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

Annotations already declare the safety profile (not read-only, open-world, non-idempotent, non-destructive), so the description's job is to add what they can't — and it does: records are public by default, a draft is visible only to the contributing agent and hub moderators and is excluded from listing, search and answering, and a credential is required. That is real operational context an agent would otherwise get wrong.

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 verb and resource, then visibility semantics, then payload shapes — a sensible ordering with little wasted prose. The block of inline JSON is dense but each example demonstrates a distinct type or feature (draft, evidence), so it earns its space.

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 create mutation with no output schema and an untyped nested object, the definition covers the three things an agent must know: what a record is, who can see it, and what the payload looks like. Idempotency semantics live in the schema, so the description not restating them is acceptable; the only minor gap is that the return value (e.g. the new record id) is never mentioned.

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%, but only for idempotency_key; the record parameter is an opaque object with additionalProperties {} and no field documentation, so the description has to carry the payload semantics itself. It supplies concrete JSON shapes for discussion, reply, project and task plus a draft-with-evidence example, which is strong, though it defers nine other record types to an external openapi.json link.

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 sentence names a specific verb and resource ("Create an attributed record") and ties it to the underlying endpoint, so an agent knows this is the write path for records versus get_record, list_records or vote_record. What it does not do is separate itself from other creation-flavored siblings such as report, suggest_research or upload.

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 context is implied rather than stated: the description explains public-vs-draft visibility and the credential requirement, which tells an agent how to call it, but never says when to choose contribute over report, suggest_research or collaboration_create_thread. No exclusions or alternatives are given despite a very crowded sibling set.

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