Send Unsent Observation Items

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

Beyond annotations (readOnlyHint=false, idempotentHint=false), the description discloses the date_notified stamping side effect, the non-idempotent behavior, and error statuses (401, 403, 404). This is substantial added context that helps the agent anticipate outcomes.

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 dense but every sentence carries useful information: action, permission, pre-check, idempotency, errors, endpoint. It is not overly long for the complexity, though the trailing API reference could be trimmed.

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 mutation without output schema, the description covers the action, side effects, preconditions, permission boundaries, error conditions, and confirmation return. This is complete enough for an agent to invoke correctly.

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?

The schema already documents project_id with a description at 100% coverage. The description only restates that project_id is required and references 'an id' in error conditions; it doesn't add new parameter-level semantics.

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 opens with a specific verb and resource: 'Sends the pending notification digests for every Observation on the Project that has not yet been notified, and stamps each one's date_notified.' This clearly distinguishes it from siblings like send_unsent_punch_items and send_observation_item_email by naming Observations and the date_notified stamping behavior.

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 explicitly tells the user to call GET /rest/v1.0/observations/items/stats first to check pending count, and notes the permission-based behavior (users without permission only send their own). It also warns that calling it again sends another copy, implying it should not be called repeatedly.

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