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

Annotations only declare readOnlyHint=true, so the description carries the burden of behavior — and it delivers richly: it guarantees the tool 'never returns a bare empty result' and explains the three response routing states (direct/broadened/redirected) so the agent knows which fallback fired. It also discloses the off-genus exclusion behavior of entity_mode='exact'. No contradiction with the readOnly annotation.

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 the core purpose and access patterns before any nuance. The match-count examples are concrete and useful. It is long (~230 words) and slightly overlaps the schema's entity_mode explanation, but every section earns its place for a 9-parameter tool; nothing is filler.

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 complex 9-param tool with an existing output schema, the description covers everything non-inferable: fallback behavior, result routing, entity resolution semantics, and the sibling contrast. Pagination and return values are already handled by schema descriptions and the output schema, so no burden falls on the description there. Complete.

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 is 3. The description adds meaning beyond the schema by enumerating the searchable content taxonomy (material, cultural reference, pigment type, historical period) and explaining the consequence of entity_mode on result composition. Some overlap exists — entity_mode and query examples are also in the schema — but the behavioral outcomes (result_path routing, exclusions) genuinely enrich parameter selection.

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?

Opens with a precise verb+resource statement: 'Full-text keyword search across all archive colour names and notes', then enumerates what can be found (name fragment, material, cultural reference, pigment type, historical period). Explicitly differentiates itself from conceptual embedding search, so an agent can tell it apart from query_conceptual and historical_colour_query without opening schemas.

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?

Names the key alternative ('Complements conceptual embedding search with exact keyword matching') and the selection criterion (exact keyword vs semantic). The examples and entity_mode discussion add practical guidance. It stops short of an explicit when-not-to-use statement for every sibling, but the contrast with conceptual search is clear enough for the main routing decision.

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