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

Despite no annotations providing safety hints (readOnlyHint=false, destructiveHint=false, etc.), the description discloses key behaviors: it costs credits, it has a byte budget for output, and it returns specific elements (quotes, provenance, coverage, continuation). It also notes that no-match is not proof of absence, which is a crucial behavioral caveat. This goes beyond the annotations and provides essential 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?

The description is concise (two sentences) and front-loaded with the core function ('Find and rank original text windows across an explicit list of sources') and key distinguishing features (BM25, no semantic search). It packs important behavioral notes (byte budget, no-match caveat, credit cost) without verbosity. Every sentence 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 tool with 7 parameters, no output schema, and no parameter descriptions in the schema, the description is quite complete. It explains the output content (exact quotes, provenance, coverage, continuation) and the byte budget, which is central to the tool's operation. It also explains cost implications. However, it doesn't describe the behavior of specific parameters like 'match_mode' or 'scope_hash', which might be needed for advanced usage. Given the complexity, it's slightly incomplete.

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%, meaning the description is the only source of parameter semantics. However, the description explains the overall output budget ('whole-response byte budget') but does not detail individual parameters like limit, start, or match_mode. Yet it does clarify that 'artifact_ids' and 'query' are used, and the schema includes detailed constraints. The description's mention of 'explicit list of sources' and 'byte budget' gives context that the schema lacks, but it doesn't fully explain all 7 parameters.

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's purpose: 'Find and rank original text windows across an explicit list of sources' with a specific retrieval method (BM25, no semantic search). It distinguishes from semantic search and clearly identifies the resource (sources) and the action (find and rank). This is a specific verb+resource pairing that differentiates it from siblings like mithrandir_search or mithrandir_query.

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 explicitly states that it searches only an explicit list of sources (artifact_ids) and does not search other accounts or the web, which is clarified again in the schema. It also warns that 'No-match is not proof of absence', guiding the agent on interpretation of results. This provides clear context on when to use this tool (when an explicit source list is available) and when not to (when a broader search is needed).

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