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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description still adds real behavior beyond that: the licensing filter on results, the exact-string (non-fuzzy) filter semantics that fail silently, and the actorCandidates fallback returned on a zero-match actor filter. That is genuinely useful operational context not present in any structured field.

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?

Front-loaded with purpose and scope, then the exact-match caveat, then the zero-match recovery path — a logical order with no filler sentences. It is somewhat dense and the exact-match point is repeated, but every sentence carries information an agent needs.

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 12-parameter, no-required-args, no-output-schema search tool, the description covers scope, filter semantics, and the zero-match recovery behavior. It stops short of describing the general result shape or pagination (limit is capped at 250 but ordering/paging behavior is unstated), which is the main remaining gap.

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%, so the baseline is 3; the description earns more by explaining that the metadata filters are exact case-insensitive full-string matches rather than substring searches, and by pointing to resolve_publisher for canonical spellings. It does not add semantics for query, since/until, relays, or authors, but the high-coverage schema already handles those.

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+resource (search educational resources), enumerates the two search modes (full-text and metadata filters), and pins the scope with an explicit inclusion/exclusion rule (only CC0/PD/CC BY/CC BY-SA returned). An agent can distinguish it from search_content or search_passages by the openly-licensed constraint alone.

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?

Clear context plus concrete routing: call resolve_publisher before actor filters, and use browse_subjects/browse_resource_types/browse_educational_levels for valid labels. It also warns that a guessed spelling silently returns 0 results. It does not, however, contrast itself against the other search_* siblings, so the alternative-selection guidance is incomplete.

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