get_previs_project_status

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

No annotations exist, so the description carries the full burden and it does substantial work: it discloses that the default path performs a live re-inspection of the target, that stale approvals are detected, that historical results are explicitly labeled, and that a fresh check fails rather than silently reporting stale approvals. Missing are permission/auth needs, cost/latency of the live check, and what the response contains.

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?

Front-loaded with the core action, then the default behavior, then the refresh=False branch, and finally the failure caveat. Three short units, each carrying information. The final sentence is slightly wordy but earns its place by preventing a wrong assumption about stale approvals.

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 2-parameter tool with no annotations, no output schema, and 0% schema description coverage, the description covers refresh semantics and failure modes well but leaves the agent guessing about project_id and about what 'revision and review history' actually returns. Adequate but with a clear gap on the required parameter.

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 must compensate. It explains the 'refresh' parameter thoroughly (default, historical labeling, failure behavior), but says nothing about 'project_id' — where it comes from, its format, or whether it must be an existing Previs project. Half the parameters are effectively undocumented.

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 and resource: 'Return revision and review history' for a project. That is concrete enough to separate it from siblings like get_previs_revision or get_previs_review_notes in spirit, but it never names those siblings, and the tool name 'project_status' does not obviously map to 'revision and review history', so a small ambiguity remains.

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?

Gives a clear default ('by default re-inspect the actual target') and an explicit alternative mode ('refresh=False returns the last recorded state'). It also states the consequence of that choice when the target is unavailable. It stops short of saying when to prefer the historical mode or naming sibling tools that also surface review data.

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