Search Project

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

Annotations declare readOnlyHint=true, so the safety profile is covered. The description adds an implicit batching/performance behavior (combining queries into one call) but doesn't disclose return format, pagination, result limits, or error behavior beyond what the schema exposes. With readOnlyHint present and schema partial, the description adds modest value but not deep behavioral 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, no filler, front-loaded with the primary action and followed by the key constraint. Every clause earns its place, explicitly stating the batching requirement and the disqualifying anti-patterns. Excellent conciseness.

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 has 10 parameters but the description only addresses the batching strategy and follow-up reading pattern. With an output schema present and partial annotation coverage, the description doesn't fully explain result semantics, limits behavior (max_total_chars, max_results_per_query truncation), or what 'partial response' means operationally. Adequate for basic use but gaps remain for a multi-parameter 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 50%, so approximately half the parameters have inline descriptions. The description itself doesn't explain individual parameters beyond the batching directive. The 'unknown or mismatched id is rejected' detail for workspace_id is helpful but lives in the schema, not the description. The description adds limited parameter nuance beyond what the schema already communicates.

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 the core action ('Batch all currently known fixed-string queries into one compact call') with a specific verb and resource, and distinguishes it from individual per-symbol search approaches. It could be clearer about being a read-only search of project content, but the batching directive makes the purpose reasonably identifiable.

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 provides explicit guidance on when to use it ('batch all currently known fixed-string queries into one compact call'), what to do after ('read returned paths with read_many_files'), and explicitly what NOT to do ('do not issue one search call per symbol'). It also names the alternative tool (read_many_files). This is strong, actionable usage guidance.

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