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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description goes beyond them by disclosing the analysis scope ('at HEAD') and exactly what the summary contains, which is meaningful behavioral context for an analytics 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?

Two sentences, front-loaded with the action and scope, then the output contents, then the user-facing question it answers. No filler, nothing repeated from the name.

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 and rich annotations, the description need not explain return values, yet it still does so helpfully. Nothing essential is missing, though a note on performance cost for large files or on large-file handling would round it out.

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 both repo_path and file documented in the schema itself, including sub-folder scoping and relative-vs-absolute path behavior. The description adds nothing about parameters, 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 ('summarize line ownership of a file at HEAD') and enumerates the concrete outputs (per-author percentages, dominant author, oldest/newest line dates). It does not name or distinguish itself from siblings like bus_factor or knowledge_risk, which also deal with ownership/risk, so the definition stops short of full sibling differentiation.

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 closing question 'who wrote / who knows this file?' implies the use case but never states when to prefer this over knowledge_risk, bus_factor, or file_history. Usage is inferable rather than explicit, which is the definition of minimum-viable 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantive behavioral detail beyond them: the silo thresholds (>= 3 commits and > 80% single-author share) and the precise bus-factor definition (>50% of commits). These thresholds tell the agent exactly how results are computed, not just that the call is safe.

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 but front-loaded: purpose, then outputs, then the bus-factor definition, then the sibling pointer. Every clause carries information an agent needs to interpret the result, with no filler sentences.

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-shape explanation is unnecessary, and the description still supplies definitions of the terms it reports (silo, bus factor). Combined with full schema coverage and annotations, nothing an agent needs to call or interpret this tool 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 the schema already documents repo_path, top, and include_merges in detail. The description adds algorithmic context but no additional meaning about the parameters themselves, 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 ('Analyze knowledge concentration by commits') and enumerates the concrete outputs: per-directory dominant author and share, silo flags, and the global bus factor. It clearly differentiates from the sibling knowledge_risk by naming it as the tool for line-level ownership.

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 routes the agent to an alternative for a related need ('For line-level ownership and inactive authors use knowledge_risk'), giving a clear condition that selects the sibling. It stops short of a full when-to-use/when-not framing for this tool itself, but the routing is unusually concrete.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real substance beyond them: rename-aware matching, and explicit exclusion of merges and huge commits. It also defines exactly how degree and jaccard are computed and what a 1.0 means, so the agent understands the semantics of 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 dense sentences, front-loaded with the core concept then the per-pair output fields and caveats. No filler; every clause (formulas, exclusions, rename-awareness) carries information the agent needs to interpret results.

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 enumerate return fields, and it still goes further by defining the metrics' meaning. Combined with the filtering caveats, an agent has everything required to call this correctly and interpret results.

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 every parameter (top, file, since, repo_path, min_shared, max_files_per_commit) is already documented, including defaults and date syntax. The description adds metric semantics (degree, jaccard, shared commits) but nothing extra about the parameters themselves, 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 analysis verb/resource: identifying files that change together in the same commits, and explicitly frames it as 'a hidden dependency static analysis cannot see', which distinguishes it conceptually from static-analysis-oriented siblings like hotspots or repo_summary. The reader immediately knows what the tool computes.

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?

Usage is implied rather than stated: the parenthetical example ('code and the test or config that must always be edited with it') suggests the investigative intent, but there is no explicit when-to-use, when-not-to-use, or named alternative among the ten siblings. Adequate but leaves the agent to infer routing.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond them: merge commits are diffed against their first parent, rename detection yields old paths, and it reports the first tag containing the commit. It omits cost/pagination behavior for very large commits, keeping it out of 5 territory.

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 'Inspect one commit' and then lists the payload; every clause carries information. The enumerated list is long but each item earns its place given the tool's breadth.

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 the extended enumeration of return fields is partly redundant, while the description still omits any usage context against the ten sibling tools. Adequate for calling the tool, but not complete for selecting 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%, with both ref and repo_path including format details (abbreviated hash, HEAD~2, sub-folder scoping) in the schema itself. The description adds no parameter-level 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 and resource ('Inspect one commit') and enumerates exactly what it returns, making the purpose unmistakable. It does not explicitly name or contrast with siblings like search_commits or find_change, so it stops short of a 5.

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

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

The description never says when to reach for this tool over search_commits, file_history, or find_change, nor does it state any prerequisite such as needing a local repo. It is purely a description of output content, leaving all routing decisions 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 already declare readOnlyHint/idempotentHint/destructiveHint, so safety is covered. The description adds genuine behavioral context beyond that: results are ordered newest first, history follows renames across the file, and rename commits carry a 'renamed_from' key.

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, with the primary scope front-loaded and the rename caveat following. No filler or redundancy.

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

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

With an output schema present and annotations covering the safety profile, the description supplies the remaining essentials: ordering, per-commit fields, and rename-following semantics. Nothing needed to invoke it correctly is missing.

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

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

Schema description coverage is 100%, so file, limit, and repo_path are fully documented in the schema itself. The description adds no parameter-level detail (e.g., default limit behavior), so it lands at the baseline 3.

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 ('List the commits that touched one file') and enumerates the returned fields (short hash, date, author, subject, added/deleted lines). It is clearly distinguishable from siblings like search_commits and commit_details.

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 scope ('one file') implies when to use it versus repo-wide tools, but there is no explicit statement of when to prefer this over search_commits, commit_details, or find_change. Usage is implied rather than spelled out.

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 safety is covered. The description adds genuine behavioral context: it explains that only commits where the occurrence count changed are returned, and that -G also matches edits and moved lines — useful for interpreting results.

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 purpose followed by a parenthetical clarification and a usage hook. Every clause earns its place with no redundancy.

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

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

For a read-only query tool with a full schema and an output schema, the description is essentially complete: it covers what it does, how it differs from -G, and a motivating use case. The only omission is routing to sibling tools for related questions.

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 all five parameters are already documented in the schema, including the file, limit, regex, and repo_path semantics. The description's -S/-G explanation reinforces the regex parameter but does not add meaning beyond what the schema already provides, 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?

States a specific verb+resource: finding commits where a code pattern appeared or disappeared, and explains the -S pickaxe mechanism vs the -G regex mode. It is very clear what it does, but it does not distinguish itself from siblings like search_commits or file_history, which an agent might otherwise confuse it with.

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?

"Great for 'when was this constant/function introduced?' forensics" gives a concrete use case and the -S vs -G contrast implies when to keep regex=false. However, there are no explicit when-not conditions or named alternative tools for adjacent use cases.

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, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: this is a multi-analysis aggregation in a single call (implying cost/latency beyond the individual tools) and it returns a {"markdown": ...} payload rather than structured rows. It does not mention any timeouts or partial-failure behavior for a composite call, which keeps it from 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?

Front-loads the deliverable, then the composition list, then the routing advice, then the return shape — a sensible ordering with no filler. The middle sentence runs long with its embedded 'AND are orphaned, single-owner or strongly coupled' qualifier, which costs a little 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?

For a five-parameter composite tool with an output schema present and full schema coverage, the description supplies everything an agent needs to choose it over siblings and predict its shape: what it aggregates, what the headline list means, when to prefer the individual tools, and that the result is Markdown. No material gaps remain.

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 of the five parameters (top, since, max_files, repo_path, inactive_after) is documented inline including defaults and git-date syntax. The description adds no parameter-level detail beyond that, so this sits at the baseline for a fully documented schema.

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

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

States a concrete deliverable (a one-call Markdown health report) and enumerates exactly which analyses it composes: repo_summary, hotspots, change_coupling, bus_factor, knowledge_risk. The definition of the 'what to look at first' heuristic (files that change often AND are orphaned, single-owner or strongly coupled) tells an agent precisely what makes this output actionable rather than just a bundle of the sibling 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?

Explicitly routes the agent: 'Use it for an overview; use the individual tools to dig into details.' The alternatives it points at are named sibling tools that appear in the composition list, so the when-to-use vs when-not-to-use split is unambiguous.

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real edge-case behavior beyond them: renames are followed (old commits counted under current name), deleted files and merge commits are excluded, and the 'hint' only appears for files with >=3 commits in the top decile. Missing details like large-repo performance or output ordering limit it below 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?

A single front-loaded sentence leads with the core action before enumerating behavior. It is dense but every clause (rename handling, exclusions, hint rule) carries information, so little is wasted.

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, return-value explanation is unnecessary, and the description covers exclusions, rename handling, and the derived 'hint'/'churn_percentile' fields. It is complete for calling the tool correctly; only sibling-relative routing guidance is absent.

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

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

Schema description coverage is 100%, so top/since/repo_path are already fully documented. The description adds only indirect meaning (top-decile and >=3-commit thresholds that relate to 'top') rather than syntax or format guidance beyond the schema.

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

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

States a specific verb (rank) and resource (frequently changed files / churn hotspots) and enumerates the metrics returned (commits per file, lines added/deleted). The scope is clearly distinguishable from siblings like file_history or change_coupling, though it never names an alternative to route against.

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

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

The description implies when the tool is useful (identifying churn-heavy files as refactoring/extra-review candidates) but gives no explicit when-to-use or when-not-to-use guidance relative to siblings such as bus_factor, knowledge_risk, or change_coupling.

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 read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. Beyond that, the description adds genuinely useful behavioral detail: the orphaned-file threshold (>50% inactive ownership), the three rollup shapes returned, and the notion that the analysis is scoped to tracked text files. It stops short of noting cost or performance implications of blaming up to max_files files.

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 tight single paragraph: the framing question is front-loaded, then method, then threshold definition, then return shape. The rhetorical opener costs little and earns its place by situating the tool. No filler or repetition.

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

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

With a full output schema, annotations covering the safety profile, and 100% parameter coverage, the description only needs to carry conceptual framing — which it does, including the analysis methodology and the orphaned-file rule. The one meaningful gap is that bus_factor, the closest sibling, is never mentioned to help the agent disambiguate.

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 schema fully documents all five parameters and the baseline of 3 applies. The description reinforces the conceptual meaning of inactive ownership (which underpins inactive_after) and the >50% rule, but adds no syntax or semantics beyond what the schema already 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 states a specific verb+resource with unusual precision: it blames tracked text files, compares line ownership against each author's last commit, and defines 'orphaned' files at >50% inactive ownership. That is enough for an agent to understand the analysis. It never names or contrasts with the nearest sibling, bus_factor, which measures a related-but-distinct concept, so sibling differentiation is absent.

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?

Usage is implied rather than stated: the lead question 'What breaks if someone leaves?' frames the scenario, and the methodology makes it clear this is a post-departure risk audit. There is no explicit when-to-use / when-not-to-use and no routing to alternatives such as bus_factor or blame_summary, which an agent must infer.

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, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds the analysis scope (calendar months ending at most recent commit) and the 'good first call' hint, but says nothing about cost, performance on large repos, or error behavior when a path is not a git repo. Adequate but not rich.

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

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

The enumeration of returned fields is front-loaded and each item earns its place for a summary tool. It is a single dense sentence plus a short routing hint; only the long itemized list risks being more detail than strictly needed.

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 needn't explain return values, and annotations cover safety; params are fully documented in the schema. The one remaining gap is usage routing — no mention of when a sibling like health_report or commit_details is the better choice.

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%: repo_path's sub-folder scoping rule and include_merges' rationale are already fully documented in the schema. The description adds no syntax or behavioral detail beyond what the input schema provides, 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?

States a specific resource (local git repository) and enumerates exactly what the summary contains: branch, commit counts, first/last commit, author count, top contributors, monthly activity. Sibling tools (health_report, bus_factor, hotspots) cover narrower analyses, and the 'Overview... Good first call' framing clearly positions this as the entry point.

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?

'Good first call' gives a clear when-to-use signal and implicitly positions it ahead of the other ten repository tools. It stops short of naming alternatives or stating when not to use it (e.g. for a single file or commit), so it lacks explicit routing.

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

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety burden is offloaded. The description usefully adds behavior the annotations cannot convey: case-insensitive matching and newest-first result ordering. Return-field enumeration is partly redundant given the output schema, but the ordering default is real 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, front-loaded with the action and scope, no filler. Every clause (case-insensitivity, filters, ordering, return shape) 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 full schema coverage, rich annotations, and an output schema, the description is sufficient for correct invocation. The only shortfall is the unstated relationship to sibling query tools, which would help an agent choose between them.

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 six parameters in detail. The description's mention of author and date filtering adds no syntax or format detail beyond the schema. Baseline 3 applies 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 ('Search commit messages') and adds scope detail: case-insensitive matching, optional author/date filters, newest-first ordering. It is distinct from commit_details by implication, but never names a sibling to differentiate explicitly, keeping it just below a 5.

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

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

The description implies usage through the filters it mentions, but gives no explicit when-to-use or when-not-to-use guidance, and does not route the agent away from similar siblings such as commit_details or find_change. Usage is inferable, not stated.

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