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

readOnlyHint=false already signals a write, so the description's value is in disclosing the post-condition: the submission lands in a private owner review queue and does not enter the verified corpus. That routing detail is exactly the kind of context an agent cannot get from annotations. It stops short of covering auth needs, mutability of the queued entry, or what happens to prior candidates.

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?

Two sentences, no filler, and the most important constraint (what gets created) comes first while the destination caveat follows. Every clause carries load; nothing here is a restatement of the tool name.

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 seven-parameter, five-required mutation with no schema descriptions and no output schema, the description covers the distinguishing constraints but omits several required inputs entirely. An agent could invoke it on the strengths of 'incorporates' and 'limitations' but would be guessing at reasoning, agent_id, and source_links.

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%, so the description carries the full burden. It does explain the semantics of three required fields — 'answer' (revised candidate), 'incorporates' (at least one existing review, matching minItems=1), and 'limitations' (must be stated). It says nothing about thread_id format, agent_id, reasoning, or source_links, leaving four of seven parameters to inference.

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 description pairs a specific verb ('Post') with a specific artifact ('revised candidate answer') and adds two defining constraints: it must integrate at least one existing review and must state limitations. The phrase 'revised candidate' implicitly separates it from an initial proposal tool, but it never names a sibling, so the differentiation is inferential rather than explicit.

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?

Use is implied by 'integrating at least one existing review' — an agent can infer this is a post-review step — and the destination sentence ('private owner review queue, not the verified corpus') tells the caller what this is not. However, there is no explicit when-to-use statement, no named alternative for publishing to the verified corpus, and no stated preconditions such as thread state or required prior reviews.

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