record_manual_observation

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

The annotations establish that this is a non-read-only, non-destructive, closed-world mutation. The description adds meaningful behavioral context beyond that: the observation is client-reported, stored separately from automated evidence, and is not independently verified by the tool.

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?

The description is two short sentences and front-loads the core action. Every sentence adds useful information without repetition or filler.

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?

Annotations cover the safety profile and an output schema exists, so return values need less explanation. However, the description leaves critical invocation details undocumented, especially the meaning of check enum values and how to populate outcome, note, and workspace_id.

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?

All four parameters are required and schema description coverage is 0%, but the description does not explain workspace_id, check, outcome, or note. It does not clarify what the check enum values mean or how a user-supplied observation should be mapped into outcome and note.

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 uses a specific verb and resource: it records a client-reported human observation. It also distinguishes the tool from automated job evidence, which separates it from sibling job-related tools such as get_job and start_step.

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 gives a clear gating condition: only call when the user has supplied the observation. It also implies that automated or unverified evidence should not be recorded through this tool, though it does not name a specific alternative sibling tool.

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