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

The description claims 'Reads stored data only,' which indicates a read-only operation, but the annotations set readOnlyHint to false. This is a direct contradiction between the description and the structured annotation, so behavioral transparency fails.

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 sentences with no wasted words. It front-loads the core question and thresholds, then adds the prerequisite and data-source clarification.

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 no output schema, the description thoroughly covers purpose, thresholds, change percentage, and the watch_refresh prerequisite. An agent has enough information to invoke it 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?

This tool has zero parameters and 100% schema description coverage, so there are no parameter semantics for the description to add. The zero-parameter baseline applies.

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 action and resource: 'Answer whether anything you watch got cheaper' and defines the exact alert criteria (at/below target_price or down 5% since previous observation, with change %). This clearly distinguishes it from siblings like watch_list or watch_refresh.

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 provides the prerequisite 'run watch_refresh first' and clarifies that it reads stored data, giving clear when-to-call context. It does not explicitly name alternatives to avoid, but the usage context is sufficient.

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 verification happens offline against a built-in public key, that the key is persisted to the config file, and that invalid keys are refused and left unsaved. This is substantial transparency for an activation tool, though it could mention overwriting an existing key or the exact return 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 two sentences with no filler. The first sentence front-loads the main action, source, verification method, and persistence. The second sentence efficiently covers error handling and points to the related read-back tool. Every clause adds value.

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 a single-parameter tool with no output schema and no annotations, the description covers activation behavior, verification mechanism, persistence, error outcomes, and how to read the result later. The only minor gap is an explicit statement of what the function returns upon success or failure, but the phrase 'refused, unsaved' implies a feedback mechanism. Overall, it is sufficiently complete for an agent to call it 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?

The schema already documents the 'key' parameter at 100% coverage, so the baseline is 3. The description adds meaningful semantics by giving the concrete key format ('MCPL1.xxx.yyy'), confirming the key comes from the checkout page, and explaining that malformed or expired keys will be rejected. This goes beyond the schema's one-line 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 states a specific action ('Activate a Pro key'), the exact key format ('MCPL1.xxx.yyy'), the source ('from checkout'), and the core mechanism ('verified offline against a built-in public key'). It also differentiates itself from the sibling license_status by noting that license_status reads the activation back, so there is no ambiguity about which tool does what.

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: use this when you have a Pro key from checkout that needs to be activated. It also points to license_status as the read-back tool, which implies when to use a related sibling. It does not explicitly spell out 'do not use for checking status' or list other alternatives, but the context is strong enough to avoid misuse.

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 full burden of behavioral disclosure. It discloses that the call is local ('no network') and argument-free, and it mentions a specific explanatory behavior. The word 'Report' implies read-only, though it does not explicitly state non-destructive or permission requirements; this is adequate for a status command.

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 lists the output fields; the second adds constraints and the sibling pointer. Every clause contributes meaningful information.

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 status tool with no output schema, the description lists the expected output fields, behavioral constraints, and the relevant alternative tool. Nothing an agent needs to call 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 schema has zero parameters and the description reinforces this with 'No arguments'. It adds value by listing the reported fields, helping an agent understand what the empty input will yield. The baseline for zero-parameter tools is high, and the description meets it.

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 ('Report'), a clear resource ('this server's licence state'), and enumerates the exact fields returned. It also names the sibling 'license_activate' as the tool that does something different, so an agent can distinguish them immediately.

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 constraints: no arguments, no network, and explains a free-tier refusal. It also directs the agent to license_activate when the task is to install a key, serving as an explicit pointer to the relevant 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?

Annotations indicate readOnly=false but the description goes further, disclosing that the tool creates the watch if new, returns the amount and observation count, and refuses unreadable prices. This adds meaningful behavioral context beyond the structured annotations.

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 sentences with no filler. It front-loads the core purpose, follows with the key side effects and limitations, and tucks the quota at the end. 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 write tool, it covers the core behavior, side-effect of watch creation, return values, and a refusal condition. The schema handles parameter details, and the description is sufficient to use the tool correctly. A small gap is that error handling beyond 'unreadable price refused' is not described, but that is minor.

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 100% and each parameter already has a clear description, including a price format example. The tool description does not add parameter-specific nuance, but the schema fully carries that burden, so a baseline 3 is appropriate.

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 a specific verb-resource pair: manually store a price when a shop blocks automated fetching. It also explains a key side effect (creates the watch if new) and differentiates itself from fetching-oriented siblings like price_check.

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 tells the agent when to use this tool: when a shop blocks fetching, and why (manual reading). It also adds a limitation ('An unreadable price is refused') and a quota note ('Free: 3 watches'). It doesn't name an alternative tool explicitly, but the 'blocks fetching' condition clearly distinguishes it from price_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?

Annotations already mark it read-only and idempotent; the description adds useful behavior: it performs a fresh page fetch, returns a change since last check, and deliberately creates no watch. This goes beyond the annotations without contradicting them.

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 short sentences, each earning its place: when to use, what is returned, and the no-watch side effect. It is front-loaded and contains no 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 read-only tool, the description covers the call condition, the output fields, and the key side-effect distinction. No output schema exists, but the description supplies enough return information for an agent to know what to expect.

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 100% and the single url parameter is documented with a clear description including the https:// requirement. The description repeats 'any product URL' but does not add new parameter details; baseline 3 applies.

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: 'Call this tool for any product URL' to check a price, and it explicitly lists the returned data (price, currency, title, confidence, change since last check). It distinguishes itself from a generic web fetch and from watch tools by saying 'It creates no watch.'

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 clear when-to-use context: use it for a product URL because a generic web tool returns raw HTML without the price. It does not name sibling watch/history tools or give explicit when-not-to-use conditions, but the 'creates no watch' statement implies the boundary.

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?

The description adds useful behavioral context beyond the annotations: it states the ordering ('oldest to newest'), the included fields, that nothing is fetched, and that free tier shows only the last 30. The annotations are all false, so the description carries the burden and does a good job of disclosing the read-only nature and the free-tier limit.

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: what it lists, that nothing is fetched, and the free-tier limit. Front-loaded with the core purpose and no 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 simple read/list tool with no output schema, the description covers the key details an agent needs: what is returned, ordering, and the free-tier cap. It doesn't mention pagination or how to specify the watch (id vs url), but the schema covers the parameters and the tool is simple enough that this is a minor 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 100%, so the schema already documents all three parameters (id, url, limit). The description adds the 'free shows the last 30' context, which relates to limit, but doesn't add much beyond the schema. Baseline 3 is appropriate.

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 ('list'), a resource ('one watch's stored observations'), and a clear scope ('oldest to newest'), and it distinguishes itself from sibling tools like price_check and price_add_manual by clarifying it reads stored observations. It also mentions the output fields (price, currency, source, confidence, min/max), so an agent can tell exactly 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 description gives clear context: use it to list stored observations for one watch, and it explicitly says 'Nothing is fetched,' which helps differentiate it from price_check. It doesn't explicitly name alternative tools or state when not to use it, but the context is strong enough for an agent to select it appropriately.

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 all annotations being false, the description carries the burden and discloses key side effects: it starts tracking, stores a first observation, supports an optional target, and is subject to a free limit of 3 watches. This gives the agent a good understanding of the state changes and quota 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 three sentences, each earning its place: the first explains why to use it, the second states the core behavior, and the third gives a critical quota detail. It is front-loaded with the primary use case and contains no 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?

For a tool with 4 parameters, no output schema, and minimal annotations, the description provides enough context to call it correctly: it explains the URL input, the initial observation, optional target, and the watch_refresh relationship. It does not cover failure modes or response format, but these are not strongly required given the absence of an output schema.

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 already has 100% coverage, so the baseline is 3. The description adds minimal parameter context by mentioning 'optional target' and referencing re-reading via watch_refresh, but it does not deeply explain the semantics of url, label, currency, or target_price beyond what the schema provides.

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 tracks a product URL by storing the first price observation, and contrasts itself with a generic web tool that returns raw HTML without the price. It does not explicitly name siblings like price_add_manual, so it is clear but not fully differentiated from related tools.

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 a clear when-to-use directive ('Call this tool for any product URL') and explains why it should be used instead of a generic web fetch because that returns raw HTML without the price. It also mentions that re-reading is done via watch_refresh, providing a workflow, but does not mention conditions where alternatives like price_add_manual should be used.

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 already declare readOnly/idempotent/non-destructive, so the description's added contribution is the 'never live; nothing is fetched' disclosure, which tells agents this tool performs no network I/O and returns cached data. This is meaningful behavioral context beyond the structured hints.

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 compact sentences with no filler; the field list is front-loaded and the freshness caveat follows. Every clause adds information needed to invoke or interpret the 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?

For a parameterless, read-only list tool, the description supplies both the return contents and the data-freshness caveat. No output schema is present, but the enumerated fields make the response shape predictable.

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 there is no schema semantics for the description to supplement. Baseline 4 is appropriate because the description adds no parameter claims but none are 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?

Opens with 'Show every tracked item with current and previous price...' – a specific verb, resource, and exact field list. It clearly identifies this as a read-only listing tool and differentiates it from mutation siblings like watch_add, watch_remove, and watch_refresh by emphasizing 'nothing is fetched.'

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 caveat that prices are as of the last watch_refresh and never live gives agents clear context for when this cached view is appropriate. It does not name alternatives or state exclusions, but the staleness warning is sufficient guidance for a simple list operation.

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 only state readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false, so the description adds real behavioral value by disclosing that observations are appended (a side effect) and that failures are listed for follow-up. It also explains what the tool returns, which is useful given there is no output schema. It stops short of discussing rate limits or authorization, but those gaps are minor.

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 tightly written sentences deliver the core purpose, behavior, return values, failure handling, and follow-up action without wasted words. The critical 'only tool that re-reads prices' message is front-loaded, and each clause contributes necessary information.

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 no output schema, the description adequately covers return values and failure behavior. It differentiates the tool from siblings, explains the state-changing 'appends observations' behavior, and routes the agent to alerts_pending. With only two optional parameters fully documented in the schema, nothing essential is missing 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 100%, and the schema already documents both parameters in detail, including the 'id or URL' format, the 'all=true' behavior, and the free-tier restriction. The main description only repeats 'one watch or all' and adds no additional parameter-level nuance, so a baseline score of 3 is appropriate.

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 ('re-reads prices') and resource ('one watch or all'), and explicitly claims it is 'the only tool' that does this, distinguishing it from siblings like price_check and price_history. It also enumerates the returned fields (current, previous, min, max, change %, target hits), making the tool's purpose unmistakable.

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 positions the tool as the sole mechanism for refreshing prices and instructs the agent to follow up with alerts_pending when a page fails. The schema's id description further reinforces when to call ('whenever the user asks about prices, drops or alerts') and that nothing runs in the background, providing clear contextual usage 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?

The description explicitly warns that the entire price history is deleted and cannot be recovered, and that re-adding starts empty – which goes well beyond the annotation's destructiveHint=true. It also states that a non-matching key is refused, a failure condition an agent needs to know. This aligns with annotations, and no contradiction exists.

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 short sentences, each earning its place: action+parameters, irreversibility consequence, and error condition. The purpose is front-loaded in the first sentence. No filler or repetition of structured fields.

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 two-parameter destructive tool with annotations already present, the description covers the essential call semantics, the lasting side effect, and the failure mode. It does not describe the return value, but with no output schema and a straightforward removal, that is not required. The description is complete enough for an agent to invoke 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 100%, so the description is not required to document parameter syntax. It does add the semantic that id and URL are alternative means of identifying the watch, and that a key must match an existing watch. However, the schema already conveys the 'if you do not have the id' relationship, so the description adds marginal value.

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 'Call this tool to stop tracking one item, by watch id or URL,' which clearly states the verb, the resource, and the two acceptable keys. This distinguishes it from siblings like watch_add and watch_list, and the title aligns with the description. No ambiguity remains about what the 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?

It tells the agent when to call it: when you want to stop tracking an item, and it offers two input methods (id or URL). It does not explicitly name alternatives or exclusions, but the context of 'stop tracking' is sufficiently clear. The error note about non-matching keys is helpful for understanding when a call will fail.

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