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

Annotations already declare readOnly/idempotent/non-destructive; the description adds behavior beyond them: the status value set, that eta.human includes queue wait, that Blender warnings surface here, that failures return the error with a log tail, and what happens when job_id is omitted. It never states scoping limits like rate limits or how long jobs are retained, so it stops short of a 5.

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 dense sentences, front-loaded with the returned fields before moving to routing and the empty-arg case. No filler, though the return-field enumeration is long and partially duplicated by the schema.

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?

An output schema exists, so return shape need not be documented, and for a single optional-parameter read tool the description covers the remaining gaps: field meanings, failure output, the no-arg listing behavior, and the sibling to use for link delivery.

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%, so the baseline is 3, but the description meaningfully adds beyond it: empty job_id lists the key's recent jobs and still-kept scene_ids, and job_id format (j_..., split finals as b_...). It does not define the queue-wait or ETA computation windows, which are only implied.

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?

Opens with a specific verb+resource ("Check a render job") and then enumerates exactly what it reports: status enum values, frames done, ETA, files ready, warnings, error log tail. An agent can distinguish it from render_info, render_download and render_cancel without opening any 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?

States the primary use case ("report progress to the user") and explicitly names the alternative for a different need: render_download(job_id, wait_seconds=45) "waits and returns the links in one call." It also spells out the no-job_id branch — listing recent jobs and retained scene_ids to resume earlier work in a new conversation.

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