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

readOnlyHint=true already signals a safe read, and the description adds genuine behavioral context beyond that: it is a diagnostic that reports absence vs presence, scopes itself to the checks' toolchain, and promises 'exact fixes for anything missing.' It does not contradict the annotation.

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?

One dense sentence that front-loads the core action and appends the conditional repo_path behavior. Efficient with no filler, though the enumeration of toolchains makes it slightly heavy to parse on first read.

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 no output schema, the description does the right amount of work: it names the scope of diagnosis and the shape of the result ('exact fixes for anything missing'). An agent knows what it will get and when the repo_path variant applies.

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 single optional parameter is fully documented in the schema, and the description goes further by explaining what repo_path actually changes: which interpreter the repo's checks would resolve and whether its test deps are installed. That adds decision-relevant meaning beyond the schema string.

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 ('Diagnose') and resource ('the local setup'), then enumerates exactly what is inspected: git, Python, node/npm, go, poetry, conda, plus repo-specific interpreter and test-dependency status. This is clearly separable from siblings like find_repos or run_relevant_checks.

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 intent (pre-flight environment diagnosis) is implied by 'the checks use' and the repo_path behavior, but the description never says when to call this versus run_relevant_checks or start_task, nor does it state any when-not conditions. Usage must be inferred.

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 declare readOnlyHint and a title, so the description carries the rest: it discloses the search scope (allowed dirs or home folder) and the result ordering (most recently active first). It stops short of stating anything about pagination/limit behavior or how deep the filesystem is walked.

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, zero filler, with the scope/ordering fact front-loaded and the usage cue second. Every clause 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?

No output schema exists, so the description must convey enough on its own; combined with the schema it covers what the tool does, where it searches, and how results are ordered. Minor gaps remain around result shape and whether the limit is honored across directories, but nothing essential to invocation 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?

At 50% schema coverage only 'query' is documented in the schema; 'limit' is undocumented. The description adds no parameter detail at all, but the undocumented param (an integer with default 20, max 50) is largely self-explanatory, so the baseline of 3 is appropriate rather than a penalty.

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 ('Find git repositories') plus scope ('on this computer, inside the allowed directories or the home folder') and ordering ('most recently active first'). It doesn't need to differentiate from siblings, which are unrelated task tools, so it stops short of a 5 only in that it doesn't frame the result set (e.g. what a 'repo' entry contains).

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?

Gives an explicit trigger with a contrasting alternative: use it when the user names a project ('my shop app') rather than supplying a path. That is clear when-to-use guidance, but it names no sibling tool to route against and states no exclusions beyond the path case.

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 readOnlyHint already declared, the bar is lower, yet the description still adds real behavioral nuance: the baseline excludes pre-existing edits, and the tool executes nothing. It doesn't cover permission requirements or performance characteristics, but the baseline semantics are a meaningful addition.

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 dense sentence that front-loads the read-only nature and enumerates the return contents; every clause earns its place with zero padding.

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?

No output schema exists, so the description correctly enumerates what comes back (files, categories, flags, selected checks). It stops short of explaining the format parameter's rendering difference, but that is already in the 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?

Schema description coverage is 100%, so both parameters (repo_path and format enum) are already documented in the schema. The description adds no parameter detail, which is the correct baseline when the schema does the heavy lifting.

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+resource ('Read-only snapshot' of task state) and enumerates exactly what the snapshot contains: changed files, impact categories, risk flags, and selected checks. 'Runs nothing' cleanly separates it from the sibling run_relevant_checks.

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 strongly implies when to use it (inspect state before executing checks), and 'Runs nothing' hints at the alternative, but no explicit when/when-not or sibling routing guidance is given.

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 readOnlyHint=false and destructiveHint=false, but the description adds a strong and valuable constraint: 'Never installs anything', which materially bounds what the agent should expect side-effects-wise. The dry_run listing behavior is also disclosed. It does not describe artifacts written or failure/timeout behavior, so it stops short of a 5.

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 dense sentences with the core action front-loaded and the check-selection policy in a parenthetical; no filler, no restatement of the title.

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 no output schema, the format parameter (markdown handoff vs json report) is covered by the schema, and the description supplies the execution policy and no-install guarantee. It could say more about what happens on check failure or how results are reported, but an agent has enough 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?

Schema coverage is 67%, and the description meaningfully augments the undocumented dry_run parameter by explaining it only lists the selection. The remaining parameters (repo_path, format) are covered by the schema descriptions, so the description adds real value on top rather than repeating.

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 action: selecting and running the cheapest meaningful checks for changed files, and enumerates the check categories (syntax, lint, typecheck, targeted tests, build, Playwright). This is clearly distinguishable from siblings like find_repos, check_setup, or verify_task, which do not run checks.

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?

Gives conditional selection context ('build when deps/config changed', 'Playwright for UI changes if configured') and explains that dry_run=true only lists the selection. However, it never states when NOT to use this tool or names an alternative among the siblings, leaving the alternative-routing gap.

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 declare it is a non-read-only, non-destructive operation. The description adds materially useful behavior beyond that: it overwrites any previous baseline for the repository, scopes writes to inside the .git directory, and explains what is captured (HEAD plus dirty-file fingerprints). These are exactly the side-effect details an agent needs before calling a mutating 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?

Three compact sentences, all front-loaded: purpose first, then the overwrite side effect, then the write scope. No filler and nothing that restates the name or annotations.

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 two-parameter tool with annotations covering the safety profile, the description provides the essential behavioral caveats. The only gap is that, with no output schema present, the agent gets no hint of what the call returns (e.g., the recorded baseline identifier), which is minor here.

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 both repo_path and task are already documented in the schema. The description adds no extra syntax, format, or constraint detail for either parameter, so the 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: record a baseline (HEAD + fingerprints of dirty files) before starting work. It clearly frames the tool's role in the verify workflow, which implicitly separates it from verify_task and inspect_task_state, though no sibling is named explicitly.

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 states the trigger condition precisely ('before starting work') and explains why (so later verification attributes only the task's own changes), which tells the agent where this fits relative to verification tools. It does not explicitly name an alternative tool or a when-not-to-use case.

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 declare readOnlyHint=true, so the description carries the interesting burden and delivers: it discloses the stale-report behavior and the fallback to a fresh inspection-only report. This is meaningful behavioral context beyond the safety hint, though return shape/pagination remain unstated.

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 tight sentences, front-loaded with the core action and immediately followed by the conditional edge-case behavior. No filler; each clause 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 read-only tool with no output schema, the description adequately explains the return behavior (stale marking, inspection-only fallback) and the schema covers the two params. Minor gap: it doesn't clarify the 'stale' semantics that would appear in the returned report.

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 both params (format enum and repo_path) are already documented in the schema. The description adds no additional parameter meaning, so the 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?

States a specific verb ('Return') and resource ('the last verification report') and distinguishes itself implicitly from siblings like run_relevant_checks and verify_task via 'without re-running checks.' It does not name an alternative sibling outright, keeping it just 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?

'Without re-running checks' implies the use case (recovering a prior report rather than generating a new one), which hints at when to prefer this over run_relevant_checks. However, there is no explicit when-to-use/when-not guidance and no sibling is named.

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 declare readOnlyHint=false and destructiveHint=false; the description explains why it is not read-only by noting it 'run[s] relevant checks', which resolves a potential ambiguity. It also discloses the output shape (evidence-labelled handoff, verdict, suggested next prompt), which the annotations do not cover. It does not contradict the 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?

A single front-loaded sentence enumerating the pipeline stages with no filler. Efficient and appropriately sized, though the dense clause list is not broken up for scannability.

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 no output schema, the description usefully characterizes what is returned (compact handoff, verdict, next prompt), filling the return-value gap. For a complex pipeline tool with four fully documented parameters, little is missing beyond explicit sibling routing.

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 repo_path, claims, notes, and format. The description only obliquely references 'the agent's claims' and adds no syntax, format, or default details 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 specific verbs and resources: inspect changes, run checks, cross-check claims, and return a handoff with a verdict. Calling itself a 'Full pipeline' distinguishes it from the piecemeal siblings (run_relevant_checks, summarize_handoff) implicitly. It stops short of explicitly naming those siblings, so it is clear but not fully differentiated.

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 'Full pipeline' framing implies this is the end-to-end option versus the granular siblings, but there is no explicit when-to-use/when-not guidance or named alternative. The agent must infer that this bundles inspect_task_state, run_relevant_checks, and summarize_handoff.

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