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

Annotations already declare a safe read, but the description adds substantial operational context: permission-scoped visibility of proposed/rejected terms and of terms by source, ordering by usage with paging and a 'total' count, null 'uses' meaning not-yet-counted, and 'similar' being gated on write membership plus an AI-plan entitlement. These are non-obvious behaviors an agent could not infer from the schema or annotations.

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?

Information-dense with no filler sentences, and the most decision-relevant facts (what is returned, state meaning, visibility) come early. The opening is a noun phrase rather than an action statement, and several clauses are nested inside dashes and parentheses, which makes first-pass parsing harder than it needs to be.

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?

There is no output schema, so the description carries the return-shape burden and does it: it documents 'total', 'kinds', 'sources', 'uses' (including the null case) and 'similar'. Combined with the annotation-covered safety profile and the 100%-covered input schema, an agent has enough to call this and interpret the response without guessing.

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 already 100%, so the baseline is 3; the description goes beyond it by unpacking the domain meaning of the 'state' values (confirmed = shown to readers and marked in texts; rejected = kept so it is not offered again) rather than merely restating the enum. It also explains the ordering and page semantics tied to 'uses'/'total'. 'kind' and 'source' syntax are left entirely to the schema.

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 opening states the resource ("A project's terms") and enumerates exactly what each record carries — word, spellings, definition, kind, source — so an agent knows what a call yields. It is clearly distinguishable from mutation siblings like set_term and merge_terms, which are mentioned by name as follow-up actions. What it lacks is an explicit verb-forward framing ("Lists...") and any contrast with term_graph or list_sources.

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 gives real situational guidance: filter by 'state', and the note that set_term with 'confirmed' or 'rejected' decides a proposed term, plus merge_terms joining 'similar' pairs when a person agrees. Visibility constraints ("Only terms whose source you may open", "listed only to members who may write") further tell the agent who will see what. It stops short of stating when to prefer term_graph over this list.

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