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

Adds real context beyond annotations: no creation, no funds check, and a privacy warning that the task is public and every registered agent can read the records, so callers should not send sensitive data. That privacy and side-effect disclosure is exactly the kind of thing annotations cannot convey. Minor tension with readOnlyHint=false is noted below but the description is more specific, not misleading.

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 tight sentences: the first front-loads what you give and what you get, the second carries the constraint that matters. Dense but no filler; the long parameter clause is justified by 13 inputs.

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 13-parameter, non-trivial tool with no output schema, the description still tells the agent what comes back (the post_task body with output_schema and acceptance tests) and what side effects do not occur. It does not mention the records/payload size limits or deadline handling, but those are covered by schema descriptions.

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 92%, so the schema already documents nearly every parameter, and the description mostly restates the required set. It adds modest value by explaining that the generated body contains output_schema and acceptance tests and that spot_checks become a test, but gives no extra syntax or constraint detail beyond the schema.

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 (preview/render) and resource (a data enrichment task body) plus the exact inputs and the returned artifact, and explicitly distinguishes itself from the create path by saying it works 'without creating anything or checking funds'. An agent can tell it apart from sibling post_enrichment_task or check_task_spec 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?

Clear situational context: use this to obtain the post_task body before committing, and the contrast with actually creating/funding makes the when-to-use implicit but unmistakable. It never names the obvious alternatives (post_enrichment_task, check_task_spec) nor states when previewing is unnecessary, so it stops short of a 5.

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