Agent Help Network

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

Annotations declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true, so the agent knows this is not a pure read and has side effects. The description adds valuable context beyond annotations: it explains that each lookup records a coarse host-level activity count, may register the host for later source refresh, clarifies that no_reports means status is unknown, and explicitly states the tool does not visit the target site. This meaningfully enriches the behavioral picture.

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 three tight sentences that are front-loaded with the core purpose and then add important caveats. There is little waste, though the sentence about no_reports and not visiting the site could be slightly condensed.

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?

An output schema exists, so return values need not be explained. Annotations cover safety and side-effect hints. However, the description does not address the three parameters at all, and with 0% schema description coverage, an agent lacks guidance on task_step and error_class. This is a notable gap for a tool with non-obvious side effects.

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% and the description does not mention or explain any of the three parameters (site_host, task_step, error_class). No meaning is added beyond the parameter names themselves, leaving required/optional roles and parameter purposes undocumented in both schema and description.

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 states a specific verb (look up) and resource (source-labeled access evidence for a public hostname), which is clearer than a generic 'check' would be. It partially distinguishes itself from the sibling report_observation by focusing on lookup/observation rather than reporting, though the relationship between the two tools is not fully articulated.

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 implies usage context by explaining what a lookup does and what no_reports means, but it never explicitly states when to use check_incident versus report_observation or other alternatives. The agent is left to infer the appropriate scenario.

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

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

Annotations already declare readOnly=false, destructive=true, idempotent=false and openWorld=true; the description usefully adds that reports go to private review and are not site-status claims, plus strict de-identification rules. However, it never explains what makes a submission 'destructive', whether repeat submissions are deduplicated, or any rate/authorization limits, leaving the most alarming annotation unexplained.

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 tightly packed sentences with the core action front-loaded and no filler. Dense but every clause (de-identification, review, non-status) carries meaning, though the phrasing is somewhat legalistic.

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?

An output schema exists, so return values need no explanation, but the many enum fields and the destructive/idempotency annotations are entirely unaddressed. For a submission tool gated by required enumerated fields and PII constraints, the description leaves significant operational gaps.

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% and the single parameter is a nested object with many enum-typed fields (outcome, error_class, challenge_kind, attempt_env, agent_family), none of which are defined in prose. The privacy exclusions ('no names, URLs, cookies, tokens') partly inform what belongs in the payload, but required fields like outcome, site_host and error_class are never explained.

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 states a concrete verb and resource ('Submit one de-identified firsthand observation') and clarifies the submission's nature ('enters private review', 'not site-status claims'). It does not reference the sibling check_incident, so an agent gets a clear purpose but must infer the boundary from the tool name alone.

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 constrains the action ('under your own operating authority and platform rules') but never says when to call this versus check_incident, nor what prerequisites exist before submitting. No when/when-not guidance is present.

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