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

With no annotations, the description carries the full behavioral burden. It usefully discloses that only the 20 most recent comments are returned, which is a real behavioral constraint, but it omits auth requirements, error behavior for missing issues, and any rate-limit 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?

A single front-loaded sentence with no filler. Every word earns its place, and the key return-content fact is stated immediately.

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 tool with no annotations and no output schema, the description covers the return shape but leaves auth, error handling, and parameter semantics undocumented. It is minimally adequate but has clear gaps.

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 0%, so owner, repo, and number have no documented meaning anywhere. The description adds no parameter detail at all, failing to compensate for the coverage gap, though the parameter names themselves are somewhat self-explanatory.

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: 'Returns an issue's body and its 20 most recent comments.' This clearly identifies the operation and scope. However, it does not differentiate itself from siblings like list_issues, search_issues, or repo_activity, so it falls 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?

No guidance is given about when to use this tool versus alternatives such as list_issues or search_issues. The description only says what is returned, leaving route selection entirely 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?

With no annotations, the description carries the full behavioral burden. It adds one useful constraint (allowlisted repository, implying a scoping/permission restriction) but omits pagination behavior, how the limit parameter is applied, ordering, and rate limits for what is clearly a paged read 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?

A single compact sentence with the resource scope front-loaded and no filler. Efficient, though it spends words on return fields while leaving the actual parameters unexplained.

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 5-parameter tool with 0% schema description coverage, no annotations, and no output schema, the description is too thin. It partially covers return fields but leaves state/limit/owner/repo semantics and pagination entirely undocumented.

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 0% across 5 parameters. The description names only 'labels' (a real parameter) while owner, repo, limit, and state are undocumented anywhere; 'author, date and comment count' are output fields, not parameters, so they do not compensate for the input gap.

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 (Lists) and resource (issues), and explicitly excludes pull requests, which is the most common ambiguity for this resource type. However it does not distinguish itself from sibling tools like search_issues or get_issue, so an agent cannot route between them from this text alone.

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?

No when-to-use guidance is given. The description never states when to prefer this over search_issues (filtered/query-based listing) or get_issue (single-item retrieval), and gives no prerequisites besides the allowlist mention.

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

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

With no annotations and no output schema, the description carries the full behavioral burden, yet it only names the categories aggregated. It does not disclose whether results are counts or breakdowns, whether the window is inclusive, or what happens for repos with no activity. "Recent period" is also vague against a days parameter with a 7-day default.

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 compact sentence front-loads the verb and resource, and every clause carries information about what is summarized. It is efficient, though it is short at the expense of the details an agent actually needs.

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

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

For a simple read-only aggregation the description covers the essential 'what,' but with no annotations and no output schema the agent has no sense of the return shape or the time-window semantics. The missing pieces are moderate rather than severe given the tool's low complexity.

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 0% across all three parameters, so the description must compensate and largely fails to. "Over a recent period" loosely gestures at the days parameter but never names it, cites its default (7), or explains the 1–90 bound; owner and repo receive no clarification beyond their self-evident names.

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 ("summarizes") over a concrete resource set (issues opened/closed, PRs merged) with a time scope, which is clearly distinguishable from the item-level siblings list_issues/get_issue. It stops short of naming those siblings or contrasting itself with them, so the differentiation is implicit 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?

There is no when-to-use guidance at all – nothing says to prefer this over list_issues or search_issues when the agent wants aggregate counts rather than individual items. The only contextual hint is the vague phrase "over a recent period," which leaves the selection decision 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?

No annotations are provided, so the description carries the full behavioral burden, and it gives almost nothing. It hints at a scoping constraint ('allowlisted repository') but omits pagination, result caps, sorting, auth requirements, and whether the query uses GitHub search syntax or free text.

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 with no filler. It is efficient, though the tightness comes at the cost of specificity rather than being paired with adequate detail.

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 three-parameter, all-required search tool with no annotations, no output schema, and no parameter documentation, this is too thin. The undefined query syntax and the owner/repo relationship leave real gaps an agent would hit at call time.

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 0%, so the description must compensate, and it does not. It gestures at 'repository' and 'query' but never explains the owner/repo split, the query syntax or operators, or the length and character constraints enforced by 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 ('Searches') and resource ('issues') with a scoping constraint ('in an allowlisted repository matching a query'). It is clear what the tool does, but it does not differentiate itself from the sibling search-like tools list_issues or get_issue, so an agent must infer the distinction.

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?

There is no when-to-use guidance and no mention of alternatives such as list_issues or get_issue. 'Matching a query' only weakly implies the search use case; nothing tells the agent when this is preferred over listing all issues.

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