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

With no annotations supplied, the description carries the full behavioral burden and does well on the most important point: it discloses the cascade that a finished job's output file is also deleted, and that the operation is irreversible. Gaps remain around whether a job still in progress is cancelled or blocked, what permission level is required, and what happens when the job does not exist.

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 short sentences, front-loaded with the action and immediately followed by the consequence and the irreversibility warning. No filler, and the most decision-relevant fact for a destructive tool is not buried.

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 one-parameter destructive tool with no annotations and no output schema, the description covers the essentials: what is removed, the side effect on output files, and irreversibility. It is only slightly short of complete, missing behavior for in-flight jobs and error/permission conditions.

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 description says nothing about the single parameter, jobId. It does not indicate the identifier format, or that ids come from render.list_for_project or render.status, so the schema's bare 'string' is all the agent has to work with.

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?

A specific verb plus resource plus scope: 'Remove a render job from the project's export list.' That cleanly separates it from render.final/preview/status/list_for_project, which produce or inspect renders rather than delete them. It stops short of naming the sibling an agent should use instead when the intent is merely to cancel or hide a render, so no explicit differentiation is stated.

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?

The description implies the usage context (cleaning up entries in the export list) and gives a strong disincentive with 'Cannot be undone,' which helps an agent decide whether to proceed. However, it never states when not to use it, nor does it point to an alternative for a render that is still in progress versus one that has finished.

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