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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), so the description's '(read only)' is redundant. However, it adds genuine context beyond the annotations: the shape of each finding (title, severity, CVSS, category, status, endpoint, remediation), the status enum values, and the caveat that findings may be false positives and need human review.

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?

Three dense, front-loaded sentences: purpose first, then payload contents, then the reliability caveat. Every sentence earns its place; only the redundant '(read only)' could be trimmed since annotations already declare it.

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?

There is no output schema, so the description carries the burden of describing return contents, and it does so well (fields, status values, severity statistics). The main remaining gap is that it does not describe pagination or result-size behavior for what could be a large findings list.

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?

Only one parameter, and schema description coverage is 100% with a clear example format ('camp_20260922_abc123') in the schema itself. The description adds nothing about campaign_id semantics, so the baseline of 3 applies.

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 the vulnerabilities and aggregated severity statistics for a Darkmoon campaign'), so an agent knows exactly what it retrieves. It does not explicitly contrast itself with siblings like list_campaigns or get_run_status, but the resource is distinct enough that differentiation is largely implicit.

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?

Usage is implied: call this to inspect the findings of a known campaign id. There is no explicit when-to-use vs alternatives guidance (e.g., when to reach for get_findings instead of get_run_status or list_campaigns), and no prerequisites stated beyond the required campaign_id.

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?

With no output schema, the description usefully discloses the exact return payload: the status vocabulary plus event count and 5 most recent events. It also explains the 'unknown' edge case as 'run log not found', which is a genuine failure-mode disclosure beyond the readOnly/openWorld annotations.

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?

One sentence, front-loaded with the verb and resource, and every clause earns its place by specifying the return content and the edge-case state. No 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?

For a simple one-param status-check tool with annotations covering safety, the description is nearly complete: it names the states and the events returned. The main gap is the polling/usage workflow and any freshness semantics, which the description omits.

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 coverage is 100% and the single run_id parameter is fully documented there as the value returned by run_pentest. The description adds no syntax, format, or sourcing detail beyond the schema, so the baseline 3 applies.

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 ("Report") and resource (Darkmoon run status) and enumerates the four possible states the tool returns. It does not differentiate itself from siblings like run_pentest or get_findings, but the purpose is unambiguous on its own.

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?

There is no guidance on when to call this versus alternatives, nor any mention that it is typically used to poll after run_pentest finishes. The only hint of context ('run_id returned by run_pentest') lives in the schema, not the description.

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 readOnlyHint and openWorldHint, so safety is covered. The description adds real value on top: it discloses that results are filtered to the calling user's visibility (an authorization scope) and that the payload carries ids and status, which the annotations do not convey.

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, no filler, with the purpose and scope front-loaded ahead of the workflow hint. Nothing is padded or redundant.

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?

With no output schema in place, the description does the right thing by naming the returned fields (ids, status). It omits ordering, pagination, or truncation behavior, a minor gap for a listing tool but not one that blocks correct invocation.

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 tool takes zero parameters, so the schema cannot be misinterpreted and there is nothing for the description to disambiguate. Baseline for a no-parameter tool is 4; it is not a 5 because there are no argument semantics to enrich.

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 (List) and resource (Darkmoon campaigns) plus the scope ('visible to the dashboard user') and what is returned (ids and status). The handoff to get_findings further anchors it against the sibling listing/retrieval tools.

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 second sentence gives explicit downstream context: take a campaign id and feed it to get_findings. It does not state when NOT to use this tool (e.g. versus get_findings directly), so it stops short of full when/when-not guidance.

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 declare the operation is non-read-only, open-world, non-idempotent and non-destructive, but the description adds material behavior beyond them: the run is asynchronous and long-running, it returns a run_id rather than findings, and results are noisy and require qualified human review. The authorization precondition and false-positive caveat are exactly the kind of disclosure an agent cannot infer from annotations.

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?

Four tightly packed sentences with zero redundancy; the core action and target scope come first, then the asynchronous lifecycle, then the safety caveat. Every sentence contributes a distinct fact.

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 an async kickoff tool with no output schema, the description supplies everything needed to invoke and follow up correctly: what it returns (run_id), the polling/reading path, the runtime characteristics, and the authorization and verification requirements. Nothing material is missing.

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 100%, so the schema already documents all four parameters (target, focus, program, severity). The description only reinforces the target constraint with 'one authorized target' and adds no format, syntax or defaulting detail beyond the schema, so the baseline of 3 applies.

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 ('Start an autonomous Darkmoon penetration test') plus the scope constraint ('against one authorized target'). The lifecycle sentence implicitly separates it from siblings by assigning get_run_status to polling, get_findings to result reading, and list_campaigns to campaign discovery, so an agent can position this as the entry point without opening another schema.

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?

Explicitly names the alternatives and the conditions that select them ('poll it with get_run_status', 'read results with get_findings once a campaign exists (list_campaigns)'). It also states an explicit when-not-to-use condition: only systems the user owns or has written authorization to test.

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