calculation_status

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description adds real behavioral context by listing what the payload contains (state, errors, checkpoint, output/report refs) and warning that call completion is not success evidence. It does not say whether polling is expected, how staleness is handled, or whether logs must be fetched separately.

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 short, dense sentences with the payload summary front-loaded and the caution second; nothing is padding. The opening is a bare noun list rather than a clause, which costs a little clarity for the compression it buys.

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?

With no output schema, the description does the necessary work of enumerating the main returned fields and flagging that state must be checked rather than assumed. What is still missing is how to proceed on a non-terminal state (re-poll? job_logs?) and how this relates to the sibling status tools.

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?

Only one nested parameter object exists and schema description coverage is 100%, with run_id and project_id each documented including provenance ('run_id returned by calculation_run', 'project id from project_create/project_list'). The description adds nothing about parameters, so the baseline of 3 applies.

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 names the payload ('run state, errors, checkpoint and output/report refs') but never states a verb+resource such as 'retrieve the status of a calculation run'; the agent must infer it is a status-read tool from the name alone. No sibling differentiation is offered against the many other status-ish tools (job_status, workflow_status, simulation_results, artifact_inspect).

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?

It gives explicit timing guidance ('Use this after reconnecting') and an explicit anti-pattern ('do not infer success from tool-call completion'), which is genuinely useful for an agent resuming a session. It stops short of naming alternatives or exclusions — nothing tells the agent when to prefer job_status or workflow_status instead.

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