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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: the markdown body is immediately published as released version 1 (an auto-release side effect), and a creator must be recorded via user_email or user_id. That is meaningful context an agent cannot get from the annotations alone.

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 purpose and the key publish/creator facts, no filler preamble. The final two sentences about file terms and multipart/form-data partially restate each other, and one of them points away from an existing sibling tool, so the tail is slightly wasteful.

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?

An output schema exists, so return values need not be explained, and the description covers the creation semantics, the creator attribution requirement, and the text-only constraint. The one gap is the absence of any reference to the multipart sibling or the version-creation tools, which is the most likely source of a wrong tool choice here.

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 description coverage is 100%, including per-property descriptions for name, body, user_email, user_id and term_type, so the schema carries the parameter burden and the baseline is 3. The description reinforces the creator requirement and the 'released version 1' semantics of body but adds no syntax or format detail beyond what the schema already states.

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 ('Create text custom terms') and immediately draws the text-vs-file boundary that separates it from the file-oriented tools. It stops short of naming the actual sibling create-custom-term_multipart_form_data, so the agent must infer the routing from the 'text only' qualifier rather than a direct pointer.

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 a when-not ('Text only; file terms are managed in the app... create file terms through the REST endpoint with multipart/form-data'), which is real guidance. However, a sibling MCP tool named create-custom-term_multipart_form_data exists in the tool set, so steering the agent to a REST endpoint instead of that sibling is at best confusing and at worst misdirecting. The 'when to use this one vs the version-creation siblings' question is not addressed at all.

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