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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: the profile is 'standing' and computed at HEAD (not the working tree), and dependents are 'null when the language is not supported,' which tells the agent to expect a nullable field rather than an error.

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 returned profile before the usage advice. Every clause adds information: the field list defines the payload, the parenthetical documents the nullable case, and the second sentence supplies use cases. 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?

With no output schema, the description carries the burden of describing returns and does so by enumerating the profile fields, including the null case for unsupported languages. Combined with 100% schema coverage on the two required params and a readOnly annotation, an agent has everything needed to select and call it.

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%: both repoDir (absolute path, any directory inside the work tree) and path (repo-relative with forward slashes, with example) are fully documented in the schema. The description adds no parameter-level detail such as path normalization behavior or error handling, 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 and resource ('Show the standing risk profile of one file at HEAD') and enumerates exactly what the profile contains: commit/bug-fix history, author count, blast radius, critical/blocked path status, top authors. The 'one file at HEAD' scope cleanly separates it from repo-wide siblings like list_hotspots and score_diff, even though no sibling is 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?

Gives two concrete triggering conditions: 'before editing a file you do not know' and 'to explain a high blast.dependents contribution.' That is clear when-to-use guidance. It stops short of naming alternatives or stating when not to use it (e.g. repo-wide analysis should use list_hotspots), so it falls just short of a 5.

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?

Goes well beyond the readOnlyHint=true annotation by disclosing the result shape ({ hotspots, warnings }), the authors-included-but-not-scored nuance, the null case for unsupported languages in the import graph, and the presence of critical/blocked path flags. This is genuinely useful behavioral detail an agent cannot get 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?

Two sentences, front-loaded with the ranking definition followed by the return/edge-case detail and the use case. Dense and slightly run-on (the return clause is a bit tangled), but almost 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?

With no output schema, the description usefully carries the return-value burden by naming the key fields and a nullable edge case, and the readOnly annotation covers the safety profile. The return description is slightly ambiguous about whether dependents and path flags are nested inside hotspots, so it is not fully airtight.

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 (repoDir, top) are already fully documented in the schema. The description adds no parameter-level detail, which matches the baseline expectation 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 and resource ('Rank the files tracked at HEAD') and enumerates the scoring inputs (bug-fix commits, churn, dependents, critical paths). An agent can tell it is a repo-wide ranking tool, though it never names siblings like explain_file_risk or score_diff to draw the boundary 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?

Gives clear context for use: 'to find where a codebase is most likely to break, or to pick files for reengineering or extra test coverage.' Strong positive guidance, but no when-not-to-use or explicit alternative routing versus the sibling 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?

Beyond the readOnlyHint annotation, it discloses the brief's contents (verdict, ranked hunks, questions, skim-safe files, unranked-hunk count), the dual Markdown/structured return, the determinism guarantee, and an explicit prompt-injection warning about quoted and backticked text. That is unusually rich behavioral context for a read-only 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 usage trigger is front-loaded and every clause carries information (sources, return shape, contents, injection caveat). It is a dense two-sentence block rather than a bloated one, though the enumeration of brief sections is long.

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?

An output schema exists, so return-value structure does not need explaining, and the description nonetheless covers purpose, trigger, provenance, and the safety caveat. Nothing an agent needs to invoke this 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?

Schema description coverage is 100%, so base, head, repoDir and maxTokens are already fully documented in the schema. The description only alludes to the two-ref diff and adds no format details, 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 names a specific artifact (a deterministic review brief for the changes between two git refs) and states its provenance (git history plus the import graph, not code reading), which meaningfully separates it from score_diff. It never names a sibling tool, so differentiation is inferential rather than explicit.

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?

"Call before reviewing a diff" gives a clear, actionable trigger for the tool. There is no explicit when-not guidance or named alternative for cases like scoring an already-summarized diff, so it stops short of a 5.

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 establish readOnlyHint=true, so safety is covered. The description adds real behavioral context beyond that: the tool emits a gate decision with reasons, flags signals it could not compute as unknowns, and optionally invokes an LLM judge, implying an external, potentially slow/non-deterministic step. It falls short of stating latency, auth, or empty-diff behavior, but adds clear value over 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?

Two sentences, front-loaded with the purpose before the usage note. The second sentence is a long enumeration of return fields, which is justified because no output schema exists, but it reads as a dense run-on rather than a tight sentence.

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 rightly enumerates what comes back (score, tier, gate decision and reasons, contributing signals, unknowns, suggested reviewers, judge rationale), and all three parameters are schema-documented. Gaps remain around empty/no-diff cases, failure modes, and the cost of the optional LLM judge, but it is nearly complete for a read-only scoring 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 100%: base, head, and repoDir each document their meaning and default values. The description frames base/head as a diff range ('between two git refs') but adds no syntax, precedence, or edge-case detail beyond the schema, 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 and resource: compute the opendrs Diff Risk Score (0-1) for changes between two git refs. The scoped artifact (a calibrated incident-probability score over a ref range) is distinct from explain_file_risk, list_hotspots, and suggest_reviewers, so an agent can route correctly 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?

Gives explicit usage timing: 'Use it before opening a pull request, or to decide whether a change should be split.' No alternatives or exclusions are named (e.g., when to prefer explain_file_risk or suggest_reviewers), so it is clear context without 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?

readOnlyHint=true already tells the agent this is a safe read, and the description adds genuinely useful context: the output is advisory only and excluded from the auto-approve gate, and the verdicts must be persisted in a specific `<!-- opendrs-self-check:v1 -->` block in the head commit message. It does not describe the shape of the returned collection itself, but behavior beyond annotations is substantially 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 trigger is front-loaded, but the body is one sprawling semicolon-chained sentence with an embedded JSON example. Much of the length is downstream workflow (how to write verdicts) rather than describing the tool, which dilutes the definition even if some of it is useful context.

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 work of naming what comes back (captain facts, reviewFirst hunks, check questions) and what each verdict means. It stops short of describing the concrete return structure (list vs. grouped object, id format), which leaves a small gap for a tool whose results must be parsed and mapped to verdicts.

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 base, head, repoDir and maxTokens are fully documented in the schema, including defaults and the 300-6000 budget range. The description adds nothing about any parameter, so 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 resource is well identified – 'the ids (captain facts, reviewFirst hunks, check questions) from the review brief' – and ties it to the sibling review_brief conceptually. The verb is only implied ('call before opening...'), which is slightly indirect, but an agent can tell this is a retrieval of self-check items rather than a diff score or hotspot list.

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 trigger is stated outright: 'Call before opening or updating a pull request.' It also scopes the purpose (pre-PR self-check) and clarifies the tool is advisory and never part of the auto-approve gate, which prevents the agent from treating the verdicts as gating criteria. Nothing about when to invoke it is left 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?

Annotations only declare readOnlyHint=true; the description adds meaningful behavior beyond that: results are capped at three, returned as author emails, and ranked by frequency of recent changes in git history. It omits edge cases (e.g., what happens with a single-commit or new repo) and any relevant auth/permission notes, but for a read-only tool this is solid added 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?

Two sentences, zero filler, front-loaded with what the tool returns and how it ranks, followed by the intended use. 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?

For a low-complexity, two-parameter read-only tool, the description covers what it returns (up to three author emails), how results are ranked, and the intended scenario. With no output schema, the description adequately compensates by describing the return shape, and no essential 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?

Schema description coverage is 100%, so both parameters (repoDir, paths) are already documented with format details ('absolute path to the git repository', 'repo-relative file paths'). The description does not extend parameter meaning beyond that, 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 and resource ('suggest up to three reviewers for a set of files') plus the ranking basis (recency-weighted git history) and the output unit (author emails). This clearly distinguishes it from siblings like score_diff, explain_file_risk, and list_hotspots, which analyze risk rather than recommend people.

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 frames the use case: 'Use it to pick human reviewers for a risky change.' That gives a clear context for invocation, but it never states when NOT to use it or names an alternative approach, so it falls short of the 5-level when/when-not guidance.

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