Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It only mentions ordering ('newest first') and fails to state that the operation is read-only, has no side effects, or describe return format or pagination—critical gaps for a tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short phrase, but it is under-specified rather than concise. It lacks a clear structure and does not front-load essential operational details; the minimal length is not justified by informative content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Though an output schema exists, the description omits crucial context such as when to call this tool, what the output contains, and how the limit parameter behaves. For a simple tool, this is still incomplete because it relies entirely on the name and schema without bridging the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not mention the 'limit' parameter at all. It adds no meaning beyond the schema's default value, failing to compensate for the lack of parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Past applications, newest first,' which conveys the tool returns a list of prior applications ordered by recency. However, it lacks an explicit verb (list/retrieve) and does not differentiate from siblings like check_already_applied or flywheel_stats, making the purpose vague rather than specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of the appropriate context (e.g., viewing submission history) or exclusions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility for behavioral disclosure. It states the action ('close' and 'release profile') but does not explain side effects such as discarding unsaved work, releasing locks, or the irreversibility of the operation. This is minimal but not contradictory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, efficient sentence that front-loads the primary action ('Close') and includes the secondary effect ('release the profile'). No filler or redundant text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple, parameterless tool with an output schema, the description adequately states what it does. It could benefit from noting that it ends the browser session, but given the simplicity, it is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema coverage is effectively 100%. The description does not need to add parameter information. A baseline of 4 is appropriate since there is nothing to clarify.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Close the automation browser and release the profile.' It clearly distinguishes itself from sibling tools like browser_open (opens) and browser_state (reads state), leaving no ambiguity about its function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives. It does not mention that it should be used at the end of a session, nor does it contrast with browser_state or browser_tabs. The agent must infer the appropriate context from the action itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden — and it excels. It discloses session persistence across runs, cookie-deletion risk from concurrent drivers, the browser_busy return with holder's name, and the constraint that the session cannot be rebuilt. These are non-obvious behaviors an agent could not infer from the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence, and every subsequent sentence earns its place by conveying a distinct operational fact: persistence, contention, cookie destruction, busy signal, and retry guidance. There is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with an output schema (which likely documents return values), the description covers purpose, session behavior, contention, and the failure mode. Minor gaps remain — e.g., what constitutes a successful open or whether the tool waits for page load — but the non-obvious operational facts are all present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It maps the single url parameter to 'a URL... in the automation browser,' which defines it adequately. However, it adds no format, scheme, or validation detail beyond what the schema's own property name 'url' already implies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence 'Open a URL in the automation browser' states a specific verb, resource, and target. This is clearly distinct from siblings like browser_tabs, browser_screenshot, browser_scroll, and browser_close, so an agent can tell them apart without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides strong operational guidance: the persistent-profile model, the single-driver constraint, the browser_busy failure signal, and explicit 'do not retry in a loop' advice. It does not explicitly name sibling alternatives or when-not conditions, but the context for correct use is clearly established.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool captures only the visible viewport, saves a screenshot, and returns a path, which is the core behavior. It does not discuss side effects or file-handling details, but this is a relatively simple read-only action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action and output, followed by a concise when-to-use explanation. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool with an output schema, the description covers what the tool does, what it returns, and when to use it. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description appropriately adds no parameter detail because there is nothing to document.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: saves a screenshot of the visible viewport and returns its path. The use-case sentence distinguishes it from DOM-reading tools, so an agent can tell what it does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context for when to use it: when the field list looks wrong or empty, because a screenshot reveals whether the page is actually in the expected state. It does not name specific alternative tools or exclusions, but the guidance is strong enough to route the agent correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states 'Scroll the viewport' without revealing any side effects, return format, or behavior details (e.g., instant vs. animated, relative vs. absolute). The tool mutates the viewport, but that is inherent. No additional behavioral context is given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short and front-loaded with the action, but it borders on under-specification. While there is no fluff, the lack of detail on `amount` and behavior makes it less useful. It is concise but not sufficiently informative to be rated higher on structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool, the description is incomplete. It fails to explain the `amount` parameter, does not describe the return value (despite an output schema being present), and gives no prerequisites (e.g., browser must be open). While the tool is simple, the description leaves essential operational details unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains the `direction` parameter ('down' or 'up') but says nothing about `amount`. Since `amount` has a default and no enum, its meaning (pixels, lines, or steps) is left entirely ambiguous. The description adds value only for direction, leaving half the parameters unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: 'Scroll the viewport.' It unambiguously identifies the tool's function and distinguishes it from all sibling tools, none of which perform scrolling. The mention of direction further clarifies the scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives, nor any context such as 'use after opening a page' or 'for long pages'. Since no sibling tool offers scrolling, the usage is implied but not explicitly articulated. There are no exclusions or alternative routing provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It discloses that refs are stable across generated markup, that required fields must be filled before submission, and that field_type determines the proper action tool. It does not explicitly state that the tool has no side effects, but the read-only verb 'List' and the overall inspection role make that sufficiently clear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded with the core action and resource. Every section earns its place: the ref usage rule, required-field warning, and field_type mapping are all necessary and presented with clean formatting. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a form-state inspection tool, the description covers the essential operational context: what is listed, how refs work, required-field behavior, and which action tool to call for each field_type. An output schema exists, so return-value details are not needed. The only notable completeness gap is the unexplained include_text parameter, but that is already penalized under parameter semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, include_text, is not mentioned anywhere in the description, and schema description coverage is 0%. The schema only provides the title 'Include Text' and a default, which is too sparse for an AI agent to know what the parameter controls. The description must compensate for the missing parameter documentation and does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'List the current page's form fields, buttons and tabs.' It clearly states what the tool produces and is not easily confused with sibling action tools like fill_field or click_target, which it explicitly references as downstream consumers of its output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains exactly how to use the returned data: pass the provided ref back to fill_field, select_option, or click_target, and use field_type to decide which action to take. It gives clear guidance, though it does not explicitly say when not to use this tool or name alternatives for list-only tabs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action but does not disclose side effects, such as whether the current tab's state is preserved, whether the switch is immediate, or any potential errors (e.g., invalid index). This is a significant gap for a tool that changes browser state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the action and resource, then specifies the parameter source. Every word earns its place, and it is appropriately sized for a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and an output schema, so the description is mostly adequate. However, the lack of behavioral details (e.g., error handling, index base) and no annotations mean an agent might not know how to handle edge cases. The reference to `browser_tabs` helps, but the description could be more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does explain that `index` refers to the tab index from `browser_tabs`, which adds meaning beyond the bare schema. However, it does not specify the index base (0-based vs 1-based) or what happens if the index is out of range, leaving some ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Make another tab the active one') and the resource (browser tab), with a specific mechanism (by index from `browser_tabs`). It distinguishes itself from sibling tools like browser_open and browser_tabs by focusing on switching among existing tabs rather than opening or listing them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: use this when you need to change the active tab, and it references `browser_tabs` as the source for the index. However, it does not explicitly state when not to use it or mention alternatives like browser_open for creating a new tab, leaving some room for inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears the behavioral transparency burden. It adds a useful non-obvious behavior—clicks may open a second tab on employer ATS sites—but it does not describe how open tabs are represented or whether the active tab is indicated. The output schema may cover return details, but the description itself adds only limited behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no filler. The primary action is front-loaded, and the second sentence adds a practical caveat about ATS sites without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-argument listing tool with an output schema, the description covers the essential action and a relevant edge case. It is nearly complete, though the timing of when to call it relative to other browser tools is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and an empty input schema, so parameter semantics are trivially satisfied. The baseline of 4 for a zero-parameter tool applies, and no additional parameter explanation is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and a clear resource ('open tabs'), making the tool's core function immediately understandable. It is distinct from sibling tools like browser_switch_tab or browser_open, though it does not explicitly differentiate itself by naming an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives such as browser_state or browser_switch_tab. The ATS note hints that it may be useful after a click, but the description leaves the usage context largely implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that matching is on job id, so the same posting via different tracking links is recognized – a useful detail. However, it does not state whether the tool is read-only, what it returns, or any edge cases (e.g., behavior when job_id is omitted). It gives one nuance but lacks comprehensive transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with zero fluff. The primary purpose is front-loaded, and the additional behavioral note is concise. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple check tool with an output schema (per context), the description is adequate but not complete. It explains the matching logic but omits details about return format, required vs optional parameters, and any preconditions. Since annotations are absent, more context would be expected, but the description covers the core functionality sufficiently for a straightforward tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only mentions job id in a behavioral context without explaining the parameters. It does not clarify that job_url is required and job_id is optional, nor does it explain the role of each. The hint that matching is on job id is helpful, but it leaves the parameters largely undefined.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: checking whether a posting was already applied to. It adds a behavioral nuance about matching on job id, which distinguishes it from URL-based matching. However, it does not explicitly differentiate from the sibling application_history, which might serve a similar role, so it doesn't fully separate itself from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (check applied status) but does not explicitly state when to use this tool versus alternatives like application_history. It offers no conditions, prerequisites, or exclusions. The mention of matching on job id hints at a use case, but there is no direct guidance on when to prefer this over other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It openly describes the automatic new-tab following and the new_tab: true report, which is a critical and non-obvious behavior. It does not cover failure behavior or broader side effects, but the key quirk is transparently disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and locator methods, then adds one high-value behavioral note with a concrete scenario. Every sentence earns its place, and there is no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is adequate for normal use: it explains what is clicked, how to target it, and an important tab-following behavior. However, the undefined 'role' and 'reason' parameters, plus the lack of guidance around when to use submit_application instead of a generic click, leave the context incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description must compensate. It explains 'name' and 'ref', but completely ignores 'role' and 'reason', leaving two of the four parameters semantically unexplained. This is a meaningful gap for a tool with no schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Click') and resource ('a button or link'), and names the two locator modes ('visible/accessible name' or 'ref'). This clearly distinguishes it from sibling tools like fill_field, browser_scroll, or submit_application.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: clicking interactive elements by name or reference. It also explains the tab-following behavior with a concrete ATS example, though it does not explicitly state when not to use it or name alternatives like submit_application.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses the Easy Apply-only limitation and the reason ('Apply on company site' hands off to an ATS whose form we have never seen), explicitly says the tool applies to nothing, and explains that the exact `search_url` is returned for traceability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded, starting with the core action and following with usage, behavioral limitations, and downstream flow. Every sentence adds either purpose, a constraint, or routing guidance; there is minimal fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, behavior, limitations, return traceability, and the correct downstream flow, and an output schema exists for result details. It is only slightly incomplete in not defining the less obvious parameters such as `recent_days` and `location`, though their defaults and names mitigate the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description needed to compensate by explaining the parameters. It only adds meaningful context to `easy_apply_only` via the default rationale; `keywords`, `location`, `limit`, and especially `recent_days` are left to be inferred from their names and types alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb-resource pair: 'Search LinkedIn for postings, newest first.' It then distinguishes itself from sibling tools by explicitly saying it only lists results and does not apply, which makes its role clear without needing to inspect other schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger: 'Use this when the user wants jobs *found* rather than handed a link.' It also states a clear exclusion ('This applies to nothing. It only lists.') and directs the agent to run the `preflight` -> apply flow on a returned job_id or url, so the downstream action is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden, and it does well: it discloses that the value is typed character by character, read back, and that mismatches are reported instead of silently succeeding. It also reveals that role and reason are recorded for future speed, providing valuable behavioral insight beyond the simple action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded: a one-sentence purpose is followed by parameter semantics and then behavioral detail. The 'no version without them' sentence is slightly emphatic but useful in preventing agents from omitting required fields. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, return values are covered elsewhere. The description covers what the tool does, when to use it, parameter meanings, recording behavior, and verification behavior. The only minor gap is not defining precisely what counts as a 'text-like field', but this is not essential for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it explains three of the four parameters: ref comes from browser_state, role names the field's purpose, and reason justifies the value. The value parameter is self-evident from the tool name and action. This is solid compensation for the schema gap, though value formatting details are not addressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence 'Type a value into a text-like field' states a specific verb and resource, making the tool's function immediately clear. It distinguishes itself from siblings like select_option, set_checkbox, and upload_file by targeting text-like fields specifically, and the role examples ('phone', 'first_name') reinforce the intended use.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states this tool is for text-like fields, which gives an agent clear context for when to use it. It does not explicitly name alternatives or state when not to use it, but the text-like field qualifier is sufficient guidance for most selection scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Because no annotations are provided, the description carries the full burden of behavioral disclosure. It does provide meaningful interpretation of the metrics and a failure signal. However, it never explicitly states that this is a read-only stat retrieval, whether values are computed live, or what effect if any the call has, leaving some assumptions implicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief and front-loads the core question of whether memory is compounding. The metric names and their interpretation are packed into two focused sentences, though the opening fragment is slightly ungrammatical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless stats tool with an output schema, the description covers the essential interpretation and a key failure mode. It does not explicitly describe when or how often to invoke the tool, or state that it is a read-only operation, but the overall picture is adequate for a simple stats check.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema already fully covers parameter semantics. The description adds value by explaining what the metrics mean and how to judge them, which is beyond what an empty parameter schema could provide.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the tool as a check on whether the memory flywheel is compounding surroundly, and pinpoints the key metrics to inspect. It lacks an explicit verb such as 'returns' or 'reports', but the intent is clear and it is not confused with siblings like record_answer or get_selector_hints.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance or mention of alternative tools. The interpretation that a `selectors_suggested` of 0 after real runs indicates a logging problem implies a monitoring use case, but it does not tell the agent when to call this tool versus related diagnostics like setup_status or guard_status.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It thoroughly discloses the behavioral outcomes of each status (answered, suggestion, need_human) and warns against paraphrasing, giving a complete picture of what the tool does and its implications.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured, starting with a clear purpose, then a usage directive, and a bulleted list of status meanings. Every sentence contributes to the agent's understanding without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter) and the presence of an output schema (not shown but implied), the description covers all necessary aspects: what it does, when to use it, how to interpret results, and subsequent actions. It is complete for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It clarifies that the 'question' parameter is the application question to look up, but doesn't provide examples or format details. Still, for a single simple string parameter, this is adequate and adds meaning beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'look up' and the resource 'previously learned answer to an application question'. It distinguishes itself from siblings like 'record_answer' (which stores) by implying a retrieval action, making the tool's purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to call this tool for every question before asking the user, and details the conditional actions for each status. It also indirectly routes to 'record_answer' when needed, providing clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full burden of behavioral disclosure. It explains that the values come from a user-editable markdown file, may not be normalized, and should be treated as exactly what the user intends. This gives important context about data provenance and reliability beyond the tool's name and schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: the first states what the tool returns, the second gives verbatim-use and fallback instructions, and the third explains why the data is authoritative. The most important guidance is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter read tool with an output schema available, the description covers everything an agent needs: what the data is, how to treat it, and what to do when a needed field is absent. No critical information is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description adds no parameter-specific semantics because none exist, which is appropriate. It focuses on behavior and usage instead.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource ('candidate's stored facts') and the purpose of the tool: retrieving authoritative form-field values. It also differentiates from the sibling `setup_status` by explaining that missing fields should be handled elsewhere, giving an agent clear resolution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent when to rely on this tool (authoritative for form fields), how to use the data (verbatim, no reformatting), and when not to infer values (call `setup_status` and ask the user instead). This is precise, actionable guidance with a named alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of explaining behavior. It adds non-obvious context: the references are 'learned from real runs,' are ranked best-first, and have two distinct consumption modes (refs vs. raw values). It does not cover failure modes or edge cases, but for a simple lookup tool this is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short paragraphs with no wasted words. The first sentence front-loads the primary purpose and ordering; the second adds provenance and practical usage nuance. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity, one-parameter lookup with an output schema, the description is mostly adequate: it explains what the tool returns, how results are ordered, and how to use them. The notable gaps are the undefined `platform` value space and the lack of explicit when-to-use guidance relative to sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate for the undocumented `platform` parameter. It only says 'for a platform,' without specifying accepted values, format, or where the platform identifier comes from. This leaves the agent under-specified on the tool's only required input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool returns 'Known-good element references for a platform' and that they are ordered 'best first.' This is specific about the resource and outcome, but it does not explicitly distinguish the tool from sibling browser-interaction tools, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives useful consumption guidance: feed refs back through `browser_state` where possible, and use raw values when a form renders differently than expected. However, it never explicitly says when to call this tool over alternatives or when not to use it, so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral disclosure burden. It implies a read-only status check by describing the current safety state, but it never explicitly states that calling it has no side effects or whether any prerequisites exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the core concept and lists the relevant status fields. There is no wasted wording or redundant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and an output schema exists, the one-line description is functionally sufficient for invoking it correctly. The main gap is the absence of usage context or an explicit read-only guarantee, especially since no annotations are present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and schema description coverage is 100%, so there are no parameter semantics for the description to clarify. The baseline of 4 applies because no parameter documentation is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as the current safety state and specifies the data it exposes: remaining quota today, failures, and whether halted. However, it lacks an explicit verb like 'returns' or 'reports' and does not differentiate itself from sibling status tools such as setup_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call guard_status versus alternatives like preflight, setup_status, or reset_halt. The description does not mention whether this should be checked before operations, after failures, or as a general health check.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It states the action but does not disclose whether the operation is read-only, has side effects, or what happens on unreachability (e.g., error vs. boolean). For a simple ping, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no waste. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, no parameters, and the presence of an output schema (not shown but indicated), the description fully covers what an agent needs to invoke it correctly. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, and the schema coverage is 100% (empty schema). The description adds no parameter information, but none is needed; baseline for zero params is 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Check') and a clear resource ('ApplyOps server reachable'), which is distinct from all sibling tools. It unambiguously tells the agent what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The purpose implies usage as a health check, but there is no explicit when-to-use guidance or mention of alternatives. Given there are no sibling health-check tools, the context is clear, though it could state prerequisites or typical invocation time.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It discloses that the tool may wait ('this call has already waited'), enforces pacing, checks the daily cap and failure breaker, and that 'allowed' false means the caller must not proceed. This is meaningful behavioral transparency beyond a simple read/write classification.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the most important instruction ('Call this first') and is dense with relevant behavioral details. It is slightly verbose with the bullet-like checklist, but every sentence contributes to correct usage. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers what the tool does, how to interpret its outcome, and the critical waiting behavior. Since an output schema exists, return-value explanation is not needed. The only notable gap is parameter semantics, which prevents a 5, but the overall flow context is strong.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain either parameter beyond the schema's names. It implies that the posting is identified via the job, but it does not clarify the role of 'job_id' vs 'job_url', why one is required, or how they relate. The description does not compensate for the low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Ask permission before starting an application. Call this first.' It names a specific verb ('ask permission'), the resource (application), and the specific checks performed. This distinguishes it from siblings like 'check_already_applied' and 'guard_status' by framing it as the first-step gate before the application flow.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit usage directive: 'Call this first' before starting an application. It explains what the tool checks and what to do when 'allowed' is false, but it does not name alternative tools or explicitly state when not to use it. This is clear context without formal exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'store' implying a mutation, but does not describe side effects, idempotency, whether it overwrites previous answers, or the return value. An agent cannot anticipate the tool's behavior beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at two sentences, with the core purpose front-loaded and the usage guideline in the second sentence. There is no wasted text, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema (not shown here), the description omits important context: what happens after storing, potential errors, and any prerequisites. Given the absence of annotations and the 0% schema coverage, the description is not complete enough for an agent to fully understand the tool's behavior and edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It mentions including 'exact wording of the question' which gives some guidance for the 'question' parameter, but it does not explain the 'answer' or 'context' parameters at all. The context parameter has a default but its purpose is unexplained. This is insufficient compensation for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool stores a user-supplied answer for future reuse, with a specific verb and resource. It also gives a concrete trigger ('immediately after the user answers something'). However, it does not explicitly differentiate from sibling tools like record_vision_fallback, which could also record user-provided data, so it's not a full 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear condition for when to call the tool (immediately after the user answers), which is helpful. But it does not mention any alternatives or when not to use it, leaving the agent to infer that this is the primary recording tool. This is adequate but not explicit about routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, so the description carries the burden. It discloses that each entry represents an adapter gap and that this is a report rather than bookkeeping, which is meaningful behavioral context. However, it does not explain whether records accumulate, whether repeated calls create duplicates, or what side effects occur besides recording.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The first sentence front-loads the action and trigger; the second adds useful semantic framing and a cross-reference to flywheel_stats. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The conceptual purpose is clearly explained and an output schema exists, but the lack of parameter documentation and the absence of annotations leave gaps for an agent trying to call this correctly. It is adequate for a simple reporter but not fully self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only indirectly references field_label as 'a field.' platform, succeeded, and dom_attempts are left undocumented; an agent must infer their meaning from names and default values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Record that the DOM locator failed and vision had to resolve a field.' It further clarifies the purpose as an 'adapter gap report, not bookkeeping,' which distinguishes it from generic logging or bookkeeping tools and from siblings like record_answer or report_failure.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The first sentence gives the exact triggering condition for use: DOM locator failure followed by vision resolving the field. The 'not bookkeeping' note and pointer to flywheel_stats().adapter_gaps help frame interpretation, though it does not explicitly name alternative tools or provide when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It transparently states that consecutive failures trip the breaker and stop the run, a side effect. It also explains that filing against a route is more valuable than just counting failures. This goes beyond the basic action and discloses consequences, though it does not mention other potential side effects like logging or state changes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: it starts with the core action, then explains rationale (breaker behavior), then parameter guidance. It is slightly verbose but every sentence adds value. The structure is front-loaded with the purpose, and the rationale is relevant for decision-making.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides sufficient context for an agent to call the tool correctly: it covers when to use it, what parameters do, and consequences. The note parameter is not explained, but an output schema exists, so return values are covered. For a tool with no annotations, this is quite complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It explains the purpose of platform, route, and blocked_at (filing the failure against a route) and implies note is optional context. It adds meaning beyond the schema by describing how these parameters affect behavior, but note is not explicitly described, leaving a small gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Report that the current application attempt failed.' This is a specific verb (report) and resource (failure), and it distinguishes itself from siblings by focusing on reporting failure rather than recording answers or checking status. The context of application attempts makes it unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool (when an attempt fails) and provides conditional guidance: 'If the attempt died at a recognisable step, pass platform, route and blocked_at.' It also explains the consequence of consecutive failures (breaker trips), which implies repeated use is discouraged. However, it does not explicitly contrast with alternatives or state when not to use it beyond the breaker effect.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the token's single-use and expiry, the requirement that `summary` list exact values, and that the tool may fill fields itself. It also implies the return includes `summary_to_show` and `confirmation_id`. This is above-average transparency, though it doesn't cover error cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with zero fluff. It opens with the purpose, then details the `summary` constraint, then the workflow and token characteristics. Every sentence adds necessary information, and the structure is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the purpose, workflow, and critical constraints, and references the next step (`submit_application`). It doesn't explain `job_url`, but that is likely self-evident and required by the schema. An output schema exists, so the description need not detail the return format. It is complete enough for correct use, though it omits prerequisites like having a job URL.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It thoroughly explains `summary` (must list fields and exact values, and call out tool-filled values). However, it does not explain `job_id` or `job_url` at all. Since `job_url` is required, this is a significant gap, though partial compensation for one parameter exists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Request approval before submitting, and get a one-time token.' It names a specific verb, resource, and outcome, and naturally distinguishes itself from the sibling `submit_application` which performs the actual submission.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit workflow guidance: show the summary, get explicit yes, then call `submit_application` with the token. It also warns about token single-use and expiry, which informs when to use this tool. It doesn't explicitly list alternatives, but the sequence is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates a state-changing action ('clear') but does not mention potential side effects, whether the operation is idempotent, permissions required, or any safety implications. For a mutating tool, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that front-loads the action and immediately gives the purpose. Every word earns its place; there is no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters) and the presence of an output schema, the description provides sufficient context for an agent to understand the core action and intent. It lacks explicit usage boundaries, but these are more relevant to the usage dimension than to overall completeness for such a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema coverage is trivially 100%. The description adds no parameter details, but none are needed; a baseline of 4 is appropriate for parameterless tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb-resource pair ('clear a tripped failure breaker') and a clear purpose ('so a run may resume'). It is immediately distinguishable from all sibling tools, which focus on browsing, filling, and application submission.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a failure breaker has tripped and a run is halted, but it does not explicitly state when to use it versus alternatives, nor does it mention any exclusions or prerequisites. The context is clear but not fully explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the output semantics (steps, human_required, runs, success_rate, hardest_gate), warns that runs: 0 means untested, and distinguishes machine-completable steps from human-required gates. This is strong context, though it does not mention side effects or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than average but every section earns its place: purpose, ordering, human interaction guidance, and data interpretation. It is structured clearly and front-loads the most important ordering constraint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the single parameter and the presence of an output schema, the description covers the key operational context: when to call it, how to treat human_required steps, and how to interpret historical route stats. It is complete enough for an agent to invoke the tool sensibly, though it omits any mention of failure or fallback behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description never explains job_url or how it should be supplied. The parameter is self-descriptive by name, but the description adds no meaning beyond the schema's existing 'Job Url' label.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly frames the tool as a route guide for a job application, explaining that it reveals what kind of application the job is and what the process will require. It differentiates the tool from browser actions by explicitly ordering it before browser_open, though it could state more directly that it returns a structured route plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit usage instruction: call this before browser_open. It also tells the agent to surface human_required steps to the user up front and how to interpret low-run routes, which is practical guidance beyond just naming the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it discloses several important behaviors: lenient number coercion, path expansion, empty values clearing a field, and the warnings/unknown_keys semantics. It could additionally clarify whether the profile is merged or replaced, but the disclosed traits are substantive and clearly stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description leads with a one-sentence purpose, then uses compact paragraphs for value parsing and response semantics. Each section earns its place and is not overly verbose for a parameter with meaningful edge cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter nested-object tool with an output schema, the description covers the essential value-coercion rules and the warning/unknown_keys response contract. It is operationally sufficient for correct invocation, though selection guidance relative to update_profile is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the only parameter is an opaque answers object with additionalProperties. The description compensates well by explaining how values map to field keys, accepted boolean forms, number coercion, path resolution, and clearing behavior, though it does not enumerate valid keys.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Store setup answers in the user's profile file,' which identifies a clear action and resource. It is specific enough to indicate a write operation for setup data, but it does not explicitly distinguish this from siblings like update_profile or record_answer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use save_profile versus update_profile or record_answer. The description implies it is for setup answers but gives no decision rules, exclusions, or alternatives, leaving the agent to infer the appropriate scenario from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses a meaningful behavior: it handles both a real <select> and a custom popup-based control. Yet it omits side effects, interaction details, and failure behavior, so transparency is only partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action front-loaded and the compatibility nuance added immediately after. Every word earns its place; no unnecessary detail or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with four required undocumented parameters and no annotations, two sentences are insufficient. The dual-format handling is helpful, but the agent still lacks parameter semantics, usage boundaries, and behavioral details needed to invoke it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description gives no explanation of the required parameters ref, value, role, or reason. With four required parameters and no schema-level documentation, the description must compensate but does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Choose an option in a dropdown.' The compatibility note about native and custom controls clarifies scope, but it does not explicitly distinguish itself from sibling tools like fill_field or click_target, so differentiation is implicit rather than named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: for dropdowns, including custom controls that open a popup, with examples like LinkedIn and Workday. However, it does not state when not to use it or mention alternatives, leaving routing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It states the core state change but does not disclose side effects, whether it simulates user interaction, how radio-group semantics are handled, or what happens when unchecking a radio button. This is a significant gap for a mutating UI tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. It efficiently conveys the primary action and target element.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with four required parameters and no annotations, the description is too sparse. It does not explain parameter semantics, clarify usage against sibling tools, or cover important behavioral details like radio grouping, making it incomplete for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain any of the four required parameters (ref, checked, role, reason). The agent is left to guess what each field means, especially role and reason, which are not self-evident.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's operation: checking or unchecking a checkbox or radio button. It is specific about the resource type, which helps distinguish it from fill_field, select_option, and click_target, though it does not explicitly name those alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus click_target or other interaction tools. The description gives no context about prerequisites, radio-group behavior, or scenarios where this tool should be preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that fields carry current values, only blank fields are re-asked, and previously answered fields are never re-asked. It also explains the single-message requirement. While it doesn't explicitly state the tool is read-only, the wording implies it only checks status and returns data. A minor gap is not mentioning error handling or edge cases, but overall it is transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured, front-loaded with purpose, then usage, then behavior. Each sentence adds value, and the guidance is clear. It is slightly verbose but not excessive; the length is justified by the need to convey usage and behavioral nuances.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the main workflow and output semantics (ready, questionnaire), and an output schema exists. However, it fails to document the only input parameter (include_optional), which is a significant omission. The description also doesn't address what happens when ready is true beyond implying no questions are needed. Overall it's adequate for the core flow but incomplete due to the parameter gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description never mentions the include_optional parameter. The agent is left with no information about what this parameter controls or how to use it. With zero schema documentation, the description should compensate, but it doesn't, making this a critical deficiency.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reports profile completeness and provides a questionnaire. It distinguishes itself from siblings like get_profile by specifying when to use it (before first application or when get_profile reports missing fields). The purpose is specific and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is given: call before the first application and any time get_profile reports missing fields. It also instructs how to handle the questionnaire (ask all at once, hand answers via save_profile) and recommends save_profile over update_profile. This is a model of usage clarity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the behavioral burden. It discloses that the tool refuses without a valid, unused token, and explains the purpose of the check ('confirm before submitting real rather than advisory'). It also clarifies the only condition under which `acknowledged: true` is permissible. It doesn't fully state side effects, but no annotations exist and nothing contradicts the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four tight sentences with the core directive front-loaded. Every sentence earns its place, and there is no filler or repetition of schema field names.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (12 parameters, high-stakes submission flow, no annotations), the description covers the critical preconditions, the acknowledgment rule, and the refusal behavior. An output schema exists, so return values need not be explained. The remaining gap is that several optional parameters are undocumented, but the essential calling context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds real meaning to `confirmation_id` and `acknowledged`, which are the most safety-critical parameters. However, schema description coverage is 0% for 12 parameters, and the other 10 parameters (e.g., `job_url`, `steps`, `answers_used`, `vision_fallbacks`) receive no explanation. This partially compensates for the schema gap but not fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Record a submitted application,' giving a clear verb and resource. It also distinguishes itself from the pre-submission step by requiring a `confirmation_id` from `request_submit_confirmation`, so an agent can tell this tool apart from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to call: 'Call this only after clicking Submit.' It also gives precise preconditions for the `confirmation_id` and for `acknowledged: true`, including the requirement that the user explicitly approved a shown summary. This is unusually concrete guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds useful context about the operation being a mid-run incremental change to known fields and implies a difference from save_profile's validation behavior, but it does not state whether unmentioned fields are preserved, what failure modes exist, or whether changes are persisted. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no filler. The action is front-loaded, followed by a concrete example scenario and a clear pointer to the sibling alternative. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter mutating tool with an output schema, the description covers the key selection and invocation context: when to call it, what it changes, and which alternative to prefer. It does not list valid profile fields or detail validation side effects, but those gaps are minor given the output schema and sibling context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has a single 'fields' object with additionalProperties: true and no property descriptions, so schema coverage is 0%. The description adds that these are 'known profile fields' and that one or a few should be supplied, which gives useful meaning to the parameter. However, it does not enumerate or describe the possible field names or value types, leaving some ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Change one or a few known profile fields mid-run.' It clearly scopes the operation to incremental, mid-run edits and explicitly distinguishes itself from save_profile by naming the alternative. An agent can tell what this tool does and how it differs from its main sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage direction: use it mid-run for a small follow-up change, and 'prefer save_profile' for initial setup because save_profile reports all validation problems at once. This directly tells the agent when to choose this tool versus the alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full behavioral burden обращения. It states the action but does not disclose side effects, validation of file_path, whether the action is reversible, required page state, or what happens after the file is attached. This is minimal but not misleading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. Every word is purposeful, and the resume hint is useful. It earns a high score for conciseness even though it lacks technical detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With four required parameters, no annotations, and no descriptions in the schema, this one-sentence description is far from complete. The agent has no way to know the purpose of ref, role, or reason, or what counts as a valid file_path.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the four required parameters. It only loosely rephrases file_path as a 'local file' and gives no meaning for ref, role, or reason. The agent cannot correctly construct the required arguments from this description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Attach') and identifies the resource ('a local file to a file input'), which is clear and distinct from generic form-filling siblings like fill_field. The parenthetical 'typically a resume' adds useful domain context. It does not explicitly contrast with sibling tools, but the file-input framing is specific enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The 'typically a resume' remark only implies a job-application context. The agent is left to infer when attaching a file is the correct action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.