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

The annotations already cover safety (readOnly, idempotent, non-destructive, closed world), so the bar is lower. The description still adds a genuinely useful behavioral trait: results are deliberately short, so an agent must follow up with get_piece to get full detail. It omits ranking, partial-match behavior, and what a result record contains.

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 tight sentences, zero filler, with the search scope front-loaded and the follow-up action stated last. Nothing could be removed without losing information.

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 simple three-parameter read tool with no output schema, this covers what an agent needs to call it correctly and to know the results are abbreviated. Slightly short of complete because result shape and matching semantics are left implicit.

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 coverage is 100%, so the baseline would be 3, but the description adds meaning the schema does not: searches span title, author, and tags, and work in both English and Spanish. That bilingual/field-coverage hint is real value beyond the parameter descriptions.

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 gives a specific verb (search) plus the resource (the whole collection) and the fields searched (title, author, tags), and explicitly points to get_piece as the follow-up action. It is clearly distinguishable from get_piece, though it does not directly distinguish itself from recommend_piece or search_open_collections.

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 clear: use this to find pieces, then open one with get_piece. It establishes the search-then-fetch workflow but offers no exclusions or guidance on when a sibling like recommend_piece would be preferable.

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