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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds genuinely new behavioral context — the new version is immediately released and used by new agreements, existing versions stay immutable, publisher identity must be recorded, and file uploads are unsupported over MCP. These are non-obvious traits beyond the annotation set.

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?

Three front-loaded sentences with no filler: the publishing action and its versioning semantics come first, then the publisher requirement, then the MCP file-upload limitation. Each sentence earns its place.

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 mutation tool with an output schema and annotations covering the safety profile, the description supplies the essential missing context: immutability of prior versions, immediate release, publisher identity, and the file-upload restriction. Only the exact body field list is left unexplained.

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 0% and the body parameter is an opaque anyOf of empty schemas, so the description must carry the load. It does add meaning by identifying the publisher fields (user_email/user_id) and implying markdown content, but it does not enumerate the actual body fields, leaving half the input surface undocumented.

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+resource ('Publish a new markdown version of text custom terms') and immediately scopes it to text terms, explicitly excluding file terms, which are handled via REST. An agent can distinguish this from create-custom-term-version_application_json and the term-creation siblings without opening a 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 clear context: use this for markdown/text term versions, and route file uploads to the REST multipart endpoint since MCP does not support them. It also names the publisher requirement (user_email or user_id). It stops short of naming the exact sibling for the JSON variant, so it is clear but not exhaustive.

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