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

Annotations only declare write + open-world + non-destructive; the description adds genuinely new facts: no AI call, post copy untouched, approval state not reset, background URL fetch with link retained on failure, and a hard 20-reference cap. That is exactly the context annotations cannot express.

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?

Five short sentences, front-loaded with purpose, then the anti-pattern warning, then the exclusivity rule, then behavioral guarantees. Every sentence carries distinct decision-relevant information.

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 4-param mutation with no output schema, the description covers the mutation's side effects, limits, exclusivity rule, and safety profile. Nothing an agent needs in order to call it correctly is missing.

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 already 100%, yet the description still adds a constraint absent from the schema: 'exactly one of text or url' (the schema has no oneOf and only requires post_id). It also explains the background-fetch behavior tied to `url`, which is the parameter's real semantics.

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?

Specific verb ('attach') plus resource ('source material to a post') with explicit scope: stored WITH the post, readable by author/reviewers, not in post copy. It cleanly distinguishes itself from save_draft/update_draft by warning against putting source text in `content`.

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?

Explicit when-to-use ('anything the post was written from') and when-not-to-use ('NEVER paste a transcript or source text into content'), and it names the sibling tools that take content instead. No inference required.

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