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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description adds real substance on top: accent-insensitive matching, all-words-must-match semantics, quote-delimited phrases, year filtering as range overlap rather than containment, and pagination via offset/next_offset. It also discloses the shape of the returned records (id, type, name, years, summary, url) even though no output schema exists.

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 dense sentences, front-loaded with the capability and followed by matching rules, output shape and pagination — no filler. The opening enumeration of record types largely restates the types enum, and the 'events' label is a small inconsistency that costs a point.

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 13-parameter, zero-required search tool with no output schema, the description covers the essentials: matching rules, filter semantics, return fields, and paging. The residual gap is the type-name mismatch ('events' vs 'post') and no hint about how multiple filters combine (AND vs OR) beyond what individual params say.

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 92%, so the baseline is 3; the description earns an increment by stating cross-parameter semantics the schema cannot express — that year_from/year_to are an overlap test on activity dates, that query matching is accent-insensitive and conjunctive, and that quoted strings become phrase queries. The only weakness is that the prose type list says 'events' while the types enum offers 'post', a small mapping the agent must infer.

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 concrete verb ('Find') and enumerates the resource domain (artists, theorists, groups, spaces, artworks, videos, annotations, contributors) plus the two search modes (free text and filters). It also explicitly contrasts itself with the sibling artlist-get, so an agent can place 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?

It routes the agent onward in both directions: 'use the get tool (artlist-get) for details' for full records, and 'See facets for the list' for valid topic names (i.e. artlist-facets). It does not explicitly say when to prefer this over artlist-related or when a filter combination is inappropriate, so it falls just short of full when/when-not guidance.

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