search_text

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a 200-page-per-call search ceiling and the fact that returned bboxes are normalized and may need expansion before cropping.

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 short sentences with the core action and return value front-loaded, then the operational constraint, then the exclusion. No filler or repetition; 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?

With no output schema, the description usefully discloses the return shape (page plus normalized bbox), and annotations cover the safety profile. However, for a five-parameter tool with zero schema documentation, an agent still lacks the parameter semantics needed to call it precisely.

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 five parameters (file, query, limit, start_page, end_page), so the description carries the full burden and largely fails: it never explains what 'limit' caps (hits vs pages), what start_page/end_page do, or the format expected for 'file'. Only an oblique hint about a 200-page ceiling is offered.

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 ('Find literal PDF text') with concrete examples (part numbers, net names) and names its return payload (page and normalized bbox). It distinguishes itself from semantic search and OCR, but does not differentiate from the page_text sibling that presumably also extracts text.

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 a clear when-not ('This is not semantic search or OCR') and a workflow directive ('expand hit bboxes before cropping surrounding circuitry'), which positions it relative to page_crop. It stops short of naming an alternative tool for full-page text extraction (e.g. page_text).

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