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

Annotations already declare idempotentHint and destructiveHint=false, but the description adds side effects they cannot express: creating the Glossary row at the end of the body if none exists, silently creating a new organisation glossary term, requiring `description` in that case, and the admin-gated 'Agents can fill a Glossary' setting for controlled releases. This is rich behavioral context beyond the structured fields.

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 action, then placement, then identification, then creation semantics, then idempotency, then the auth caveat. Dense but each clause carries information; only the parenthesis about [[glossary]] is slightly incidental.

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 6-parameter mutation with annotations but no output schema, the description covers conditional parameter requirements, side effects on the org glossary, idempotency, and permission gating. The main omission is any indication of what the call returns or how errors surface, which is minor given no output schema is declared.

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% and the schema already documents every parameter, so the baseline is 3. The description nonetheless adds conditional semantics the schema does not: description is required only when the term is new, kind/categories apply only to new terms, and termId and term are alternative identifying paths. That conditional logic is genuine value-add.

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?

States a specific verb and resource ('Add a term to this document's Glossary') and immediately distinguishes itself from the read-side sibling by pointing to traceable_glossary_search as the source of termId. An agent can tell it apart from glossary_search and from block-writing tools without opening either 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?

Gives concrete guidance: reference an existing term via termId from traceable_glossary_search, or pass raw text in `term`. It also explains the placement alternative ('write [[glossary]] there first') and the controlled-release prerequisite. It stops short of an explicit when-to-use-vs-alternatives rule, but the routing is clear.

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