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

No annotations exist, so the description carries the full burden, and it does disclose real behavior: drafts are supported and non-draft finds hit the published main-table state, the collection is public-read via /api/agents, and shortDefinition is auto-consumed by tooltips and AI answers. It also warns that delete is a permanent hard-delete bypassing the admin Trash, which is valuable context even if it belongs to a sibling mutation tool rather than this find tool.

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?

It is front-loaded with a useful field-and-behavior dump but then appends a long schema recap ("Fields: title (localized), slug (localized), synonyms (localized), ... searchText (textarea, localized, ≤60000 chars, redacted), meta (group: ...)") that largely restates collection metadata. Capability, delete, and writing-guideline sentences target create/update/delete and add noise for an agent deciding how to call this read tool.

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?

With 10 optional params at 100% schema coverage and no output schema, the description supplies the domain model, draft behavior, locale handling, and field inventory needed to form useful where/select clauses. It omits any hint about response shape or pagination totals, but pagination is already covered by the schema's page/limit descriptions.

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 earns an extra point by explaining draft semantics in a way the schema's vague wording ("versions table/collection") does not. It also enumerates the fields available for where/select/sort (title, slug, synonyms, tags, related, robots), giving the agent concrete field names the generic schema cannot supply.

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 opens with "Public glossary of terms," which identifies the resource but never states a clean verb+scope sentence like "retrieve glossary entries." The verb only surfaces obliquely in "a find WITHOUT draft:true returns the published main-table state" and in the boilerplate "MCP capabilities: find, create, update, delete," which lists four operations for a tool whose schema only supports querying. Sibling differentiation is mostly carried by the tool name (findGlossary vs findFaqs), not the text.

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?

There is a concrete conditional: "a find WITHOUT draft:true returns the published main-table state only," which tells the agent when to pass draft. It also routes to a sibling, "Before writing public text here, call getWritingGuidelines with this collection and the locale," but that guidance only applies to write operations, not to this read tool. No when-not-to-use or alternative-for-filtering guidance is given.

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