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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds a genuinely non-obvious behavior: on a miss it suggests close matches instead of failing, which tells the agent how to handle imperfect queries. It also lists the returned fields, but that is partly redundant with the output schema.

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?

Two compact sentences, front-loaded with what is returned, followed immediately by the fallback behavior. Nothing is padding.

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 one-parameter, read-only lookup with full annotations and an output schema, the description covers the essentials, including no-match handling. Minor gaps remain around matching rules (case sensitivity, aliases), which are left to chance.

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?

One required parameter with 100% schema coverage, so the baseline is already high. The description still adds value by illustrating the expected term format with two real examples, reducing the risk of the agent passing an ID or a natural-language question instead of a term.

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?

Names a specific verb (return) and resource (Protoperfect glossary definition), and enumerates the payload: category, related terms, source paper. The concrete term examples ("Warranted Agency", "Context Window") make the resource unmistakable versus the document-oriented siblings.

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?

Usage is only implied by the resource type: an agent infers this is the tool for looking up a glossary term rather than fetching a document. It never explicitly says when to prefer it over search_documents or get_document, and offers no exclusions.

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