search

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds a genuinely non-obvious behavioral trait: results are marked untrusted and are not instructions, which is important for an agent handling injected text. It does not cover result shape or ranking behavior, but the untrusted-content warning is meaningful 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?

Three sentences, front-loaded with purpose, then usage, then a safety note; each sentence adds distinct value 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?

An output schema exists so return values need no explanation, and annotations cover the safety profile, which the description reinforces with the untrusted-content note. The only real gap is the undocumented days/limit parameters, which slightly undercut completeness for a 3-param 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 0% for three parameters, so the description carries the burden but only 'query' is self-evident from 'full-text search'. The 'days' (recency window) and 'limit' (max results) parameters are left completely unexplained in both schema and description.

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 (full-text search over document narratives) and enumerates the content types covered (doctors' conclusions, immunogram interpretations, ultrasound descriptions). It also implicitly distinguishes itself from numeric siblings like query_observations and sql_query by framing the answer as 'text, not numbers'.

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?

Gives concrete triggering questions ('what did the immunologist say', 'why polycythemia') and states the selection condition ('where the answer is in text, not numbers'), which usefully excludes numeric tools. It does not name specific sibling tools as alternatives, so it stops short of a 5.

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