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

Annotations already declare readOnlyHint true and openWorldHint false, and the description adds real behavioral content on top: results arrive as numbered cited sources including related commits, claims must be cited as path:start-end, and there is an answer-from-sources-only rule. Output format is partly covered by the output schema, so the remaining detail is appropriate rather than a 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 densely front-loaded, leading with what the tool does and following with usage rules and routing. It is compressed almost to note form, but every sentence carries an instruction and there is 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?

Annotations cover safety and an output schema exists, so the description does not need to explain returned structure. It still covers purpose, triggering conditions, citation format, and the alternatives, which is complete for a retrieval tool of moderate complexity; only the sourcing or ranking behavior 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?

Schema description coverage is 100%, so k, repo, and question are already documented, and the description adds no parameter-level detail. The baseline 3 is correct when the schema does all the work.

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 output: gather the code and docs most relevant to a question, plus related commits, returned as numbered cited sources. It is clearly distinguishable from search (filters) and read_lines (full source), both of which are 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 concrete triggering questions ("how does X work?", "where is Y handled?") and explicitly routes the agent elsewhere: use search for filters and read_lines to open a source in full. It also imposes an answering constraint (answer from these sources only), so the agent knows what the tool is for and what it is not.

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/openWorldHint annotations, the description discloses the concrete payload (author of current lines, every commit that changed them with relevant diffs, and PR title/description) and flags a real caveat — PR metadata is GitHub-only. It does not explain behavior when both symbol and path are supplied, or when neither is, which is the remaining operational ambiguity.

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 dense sentences with the motivation front-loaded, then usage, then inputs, then outputs. No filler and no repetition of schema text verbatim.

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 six optional parameters, an output schema present, and safety already covered by annotations, the description carries the right load: purpose, trigger, selector modes, and the GitHub caveat. Complete enough to call correctly; only the both-params/neither-param edge cases are 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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema only hints at: it frames symbol and path as mutually alternative selectors and makes the line range explicitly optional and subordinate to path. The GitHub-only qualifier is also the only place backend support is tied to the output content.

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 concrete framing ('Why code looks the way it does') and states both input modes (a symbol, or a path with an optional line range) plus the shape of the answer. It is clearly a blast-radius / provenance tool, distinguishable in spirit from search_history, but it never names that sibling or draws an explicit boundary against it.

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 scenario: use it before removing or rewriting code that looks odd, or when answering 'why is it like this?'. That is genuine when-to-use guidance. It stops short of exclusions or naming alternatives such as search_history or impact_of_change, so the agent must infer which history tool to pick.

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=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context — findings carry a severity, cite the doc section, and include a suggested fix, and changelogs are excluded — but it does not say whether analysis is post-index only (requiring index_repo first), how expensive a full-repo scan is, or whether results are ordered deterministically. Those gaps keep it at solid-but-partial rather than 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?

Dense and front-loaded: the problem statement, then use cases, then the specific detection categories, then the changelog exclusion. The fragment style in the opening sentence and the semicolon-chained finding list are slightly unruly but every clause carries 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?

With an output schema present, the description need not explain return shape, and annotations cover read-only safety; the remaining burden is telling the agent what the tool checks and when to reach for it, which it does. The only shortfall is that it does not state the prerequisite of an indexed repo, which is instead buried in the repo parameter's schema description.

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 each of the four parameters is already documented, including repo lookup via list_repos and the 1-200 limit bound. The description adds nothing parameter-specific beyond a vague nod to checking a "docs folder" (path_prefix) and release timing; baseline 3 applies when the schema does all the work.

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 line names the resource and the problem domain (docs that no longer match code), and the middle of the description enumerates exactly what it detects: missing files/functions/settings/flags, bad parameters, failing imports, stale sections. That is far more specific than a sibling like search or ask_codebase, though it never explicitly contrasts itself with those siblings, and the leading sentence is a noun phrase rather than a verb+resource statement.

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?

"Use this to check a README or docs folder, or before a release" gives concrete triggering situations, and "Changelogs are skipped" supplies an explicit exclusion. What's missing is naming the alternatives an agent should pick instead when it wants code search or history (search, explain_history) for a drift-adjacent question.

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/openWorldHint annotations, it discloses the analysis is structural and limited to Python, JavaScript and TypeScript, and critically that matches are name-based so results may include false positives flagged in 'same-name notes'. Those precision caveats are exactly the behavioral context an agent needs before trusting the output.

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, front-loaded with the outcome the agent cares about, then the usage trigger, then the caveat. Every clause carries information: scope, languages, matching caveat, and the test follow-up.

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 a full input schema and an output schema present, the description need not explain return shape; it instead spends its space on language coverage, matching limitations, and pre-edit workflow — the pieces not covered by structured fields. Nothing an agent needs to invoke it correctly appears to be 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 coverage is 100% and each parameter (path, repo, depth, symbol) already carries its own description, so the schema does the heavy lifting. The description adds no extra syntax or format guidance for depth levels or repo scoping, which is the expected baseline when the schema is fully documented.

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 question the tool answers ('What breaks if a symbol changes') and enumerates the exact result classes: direct users, transitive users, and involved tests. That verb-plus-resource framing makes it immediately distinguishable from siblings such as search, ask_codebase, or explain_history.

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 concrete trigger ('Use this before editing a shared function') and a follow-up action ('run or update the tests it lists'), which tells the agent when this tool is the right call. It stops short of naming an explicit alternative or exclusion (e.g. when to prefer search or explain_history instead).

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 the mutation/idempotent/open-world profile, but the description adds genuine context beyond them: re-runs only re-embed changed files, URLs are cloned blobless with full history so explain_history works, and progress is reported during the run. The only thing not covered is whether re-indexing can overwrite or drop an existing index under the same name.

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?

Four short sentences, front-loaded with the purpose and the 'use first' rule, then incremental re-index behavior, then clone semantics, then return/progress info. No filler and nothing repeated from the schema.

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 an indexing/setup tool with two parameters, an output schema and full annotations, the description covers everything an agent needs to decide to call it, when to re-call it, and what side effects 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%, so the baseline is 3; the description goes slightly beyond by explaining what a URL source actually does (blobless clone with full history), which is behavior an agent needs when choosing between a local path and a remote URL.

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 first sentence states a specific verb and resource ('Index a repository') and ties the purpose to the sibling ecosystem ('so the other tools can search it'), immediately distinguishing it from search, ask_codebase, explain_history and the read-only 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 it ('Use this first') and when to call it again ('again after the code changes'), with the reason re-running is cheap. That ordering constraint is the critical usage fact no sibling name or schema field conveys.

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 and closed-world behavior, so the description only needs to add context beyond them. It does so by disclosing the result set is limited to repos already indexed and that entries are tied to a specific indexing commit. It says nothing about empty results or staleness of the index, which keeps it below the top band.

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, no filler. The result content is front-loaded and the workflow instruction follows, so an agent can act on the first clause alone.

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 no-argument tool with an output schema and read-only annotations, the description covers everything needed to decide to call it and to know what comes back. Return-field detail is legitimately delegated to the 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 tool takes no parameters, so the baseline of 4 applies; there is no input semantics for the description to explain. The description correctly spends its space on output scope instead of inventing parameter detail.

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?

Names a specific verb and resource (list repositories) and states what each entry carries: size, languages, and the commit it was indexed at. The scope phrase 'indexed so far' separates it from index_repo, which is the tool that adds 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?

Gives explicit ordering guidance ('Use this first') and a concrete reason: to obtain the repo names that the other tools require. It does not name a competing alternative or state when-not to call it, but for a zero-argument entry-point tool that guidance 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description only needs to add constraints. It does so usefully by stating the tool 'Refuses paths outside the repo', which tells the agent a sandbox boundary exists and invalid paths will error rather than silently resolve. Return-format detail is delegated to the output schema, which is appropriate.

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, purpose front-loaded, followed by the use condition and then the safety constraint. No filler and nothing repeated from 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?

With annotations and an output schema present, the description covers purpose, trigger, and the repo-boundary constraint, which is enough to call the tool correctly. It leaves unaddressed edge behavior such as out-of-range start/end values or any cap on range size, a minor gap for a read 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%, so path, start, end, and repo are all already documented in the schema, including 1-based indexing and the inclusive end. The description adds no extra syntax or range semantics beyond that, so the baseline of 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 ('Exact, numbered lines from a file in an indexed repo') and scopes it to a repo. It also distinguishes itself from the snippet-based search sibling by noting that 'search results are trimmed snippets'.

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 a concrete trigger for use: open a citation in full before quoting or editing it. The alternative (search snippets) is implied clearly, but there is no explicit when-not-to-use guidance, such as preferring search for discovery.

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=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the two retrieval strategies and how they are fused, plus the shape of each returned chunk (path:start-end citation, symbol, snippet). It stops short of covering result-quality caveats or how ranking ties break, but that is a minor omission given the annotations and output 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 tight sentences: mechanism first, selection guidance second, return shape last. No filler and no restatement of the tool name or schema.

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 five fully documented parameters, a present output schema and read-only annotations, the remaining burden on the description is mechanism, alternatives and result shape — all three are covered. Nothing an agent needs in order to call 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%, and the schema already documents k, repo, kinds, query and path_prefix in detail. The description only gestures at filter usage ("filters by folder or chunk kind") without adding syntax or semantics 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?

"Hybrid search over code and docs (BM25 keywords plus local embeddings, fused by rank)" names a specific verb and resource and explains the retrieval mechanism in the same breath. It also implicitly separates itself from prose-answering siblings like ask_codebase, so an agent can pick it 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?

Explicit positive cases ("targeted lookup", "when you need filters by folder or chunk kind") and an explicit negative with the named alternative ("for a question you'll answer in prose, use ask_codebase instead"). Both branches of the decision are stated.

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=true and openWorldHint=false, so safety is covered. The description adds meaningful behavioral context by scoping the match to commit message text rather than diffs or code, which prevents a likely misuse; it does not discuss ranking or result ordering, but the output schema covers the return shape.

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: scope, use cases, and the redirect to an alternative. The key disambiguation is placed after the core purpose but nothing is buried or padded.

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 three-parameter read-only search with a fully documented schema and an output schema, the description covers purpose, usage, and the nearest competing tool. An agent has everything needed 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?

Schema description coverage is 100%, with k, repo, and query all documented including defaults and the single-repo case, so the schema carries the parameter burden. The description reinforces the query semantics ('words from commit messages') with an example but adds no syntax or format detail beyond what the schema already states.

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 -- 'Find commits by what their messages say' -- which immediately separates it from code-content search. It also explicitly names the sibling tool explain_history as the one to use for a different scope, so the agent can discriminate 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?

It supplies two concrete natural-language questions this tool answers ('when did we change X?', 'which commit fixed Y?') and an explicit when-not rule routing function/file history to explain_history. Both the use case and the alternative are stated, leaving nothing to inference.

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