atlas_auto_incidents_pending

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

With no annotations, the description carries the full burden for behavioral disclosure. It states the tool returns machine-drafted incidents queued for human review, implying a read-only operation. However, it does not mention whether results are sorted, paginated, or limited to un-reviewed items. Some additional behavioral context (e.g., default ordering, count limits) would be beneficial.

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 sentences, each serving a clear purpose. The first sentence states what the tool does and the information it provides. The second sentence distinguishes it from a sibling tool. No fluff, front-loaded with core purpose. Extremely efficient.

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?

Given the tool has no parameters and no output schema, the description covers the essential information: what it returns and how it differs from a related tool. It mentions the fields included. However, it could be more complete by indicating whether results are ordered (e.g., by date or confidence) and if there is any filtering applied (e.g., only pending incidents). Still, for a simple retrieval tool, this is largely sufficient.

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 input schema is empty (no parameters), so schema_description_coverage is 100% trivially. The description adds meaning beyond the schema by detailing the content of the returned data (country, mechanism, evidence, confidence). For a parameterless tool, the description effectively explains what the agent will receive.

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 clearly states the tool returns machine-drafted incidents auto-generated and queued for human review, with specific fields (country, mechanism, evidence, confidence). It explicitly distinguishes itself from sibling atlas_auto_findings_queue by noting 'this one is full incident drafts, not finding cards.' Purpose is specific, verb+resource, and disambiguated.

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 provides context on when to use this tool by comparing it to atlas_auto_findings_queue. It clarifies that this tool returns full incident drafts rather than finding cards, helping an agent choose between the two. However, it does not specify when to use this tool vs other incident-related tools like get_incident_detail or get_incidents_since.

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