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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the description doesn't need to repeat safety. It does add real behavioral value: every row carries `source_type` and exactly one of `external_url` (stream) or `media_url` (file), never both — a non-obvious invariant an agent must know to interpret results. It doesn't cover ordering, ranking or pagination limits, which keeps it off a 5.

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, each earning its place: purpose and corpus scope first, match semantics second, row shape last. The parenthetical about item descriptions being 'the richest text most of these items have' is a useful justification for keyword behavior, not padding.

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?

Nine optional parameters with no output schema, and the description covers both what the corpus contains and what a returned row looks like, which is the main gap elsewhere. What's absent is result ordering/ranking and how limit/offset behave across a full result set — minor but relevant for a search tool an agent may page through.

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 89%, so per-field syntax is already documented. The description still adds meaning beyond it by enumerating precisely which fields a `keyword` matches (title, creator, publisher, subject, spatial, language, source, item description and transcription), which the schema only calls 'title/metadata fields'. That enumeration clarifies matching behavior rather than restating parameter definitions.

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 resource (audiovisual materials), then names the exact scope: francophone web video from Burkina Faso, Togo and Benin plus deposited Nigerian Hausa/Arabic recordings. That scope definition is what separates it from list_audiovisual, get_audiovisual and the generic search sibling, so an agent can pick it without opening a schema.

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 material description (which corpora it covers, what keyword matches), and the schema hints at filter choice (prefer publisher/keyword over subject). But the description never states when to choose this over list_audiovisual or the generic search, nor any exclusions or prerequisites. Adequate context, no routing guidance.

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