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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety bar is low. The description adds genuine behavior beyond that: it returns at most five pieces each with a short answer and a link, and it branches on crisis-sounding input to return crisis lines by country rather than pieces — a non-obvious runtime behavior an agent could not infer from structured fields.

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 the verb and resource, then the return shape, then the exclusions. Little waste, though the final crisis sentence is convoluted ('written in its text, instead of pieces') and takes a re-read to parse.

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 explains the return shape (up to five pieces, short answer plus link) and pre-empts the main misread by declaring it is not medical or crisis help and what happens on crisis input. A low-complexity, three-parameter, fully-documented search tool is adequately covered.

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 100%, with the limit range, the query length cap and the 200-character search truncation all documented in the schema itself. The description only echoes 'up to five pieces', which maps to the limit maximum, and adds no new meaning for query or topic. Baseline 3 applies.

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 (Search) and a specific, well-characterized resource: a library of short essays on inner life, burnout, grief, relationships, meditation and work, with named authors. An agent can tell what content domain it covers. It does not explicitly distinguish itself from siblings like find_practice or get_piece, so it stops short of 5.

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?

Usage is implied by the framing (a question in plain words) and there is a real scope exclusion — 'Not medical, therapy or crisis help' — plus a described fallback when the query reads as crisis. However, it never says when to use this versus find_practice or get_piece, and no prerequisites or exclusions relative to siblings are given.

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