search_patches

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

No annotations are provided, so the description carries the full burden. It discloses that it returns a dictionary of matching patches and evidence sources but does not explain behavioral traits such as match semantics, ordering, pagination, or any constraints on the query or filters.

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 concise and well-structured, with a clear purpose sentence followed by a compact Args list and Returns line. Every sentence provides useful information without 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?

The tool is relatively simple and output schema exists, but the description omits details like how results are ordered, whether query supports partial/fuzzy matching, and definitions of states or subsystems. It is adequate for basic use but lacks depth for more nuanced searches.

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%, but the description adds one-line meanings for each parameter (e.g., query searches patch name, limit is max results). This is helpful but lacks detail like valid state values or subsystem naming conventions.

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 clearly states the tool searches submitted kernel patches by query, submitter, or state, with a specific verb and resource. It distinguishes itself from sibling tools like search_commits and search_kernel_code by targeting patches specifically.

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 for finding patches but does not provide explicit guidance on when to prefer it over related tools like get_patch_details or analyze_patch_series. It offers clear context for the search action but no exclusions or alternative recommendations.

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