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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: it is a cheap incremental check, it returns changed devices plus their new hash, and it imposes a strict input-privacy rule (no host names, IPs, MACs, user or site names).

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?

Short and front-loaded, with the identity of the tool and the workflow constraint stated first and the privacy warning last. 'Use this for repeat checks' lightly restates the opening phrase, a minor redundancy rather than bloat.

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 return-value duty and does so: it explains that changed devices and their new hash come back. Combined with the input-privacy rule and the follow-up guidance, nothing needed to invoke it correctly 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 coverage is 100%, so the baseline is 3. The description still earns credit by explaining the workflow contract — reuse the same vendor/product/version plus the retained result_hash from correlate_devices — and by adding a privacy constraint that the schema only partially mirrors ('Never a host name or address').

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+resource framing ('Cheap repeat check') and immediately scopes it to devices previously processed by correlate_devices. An agent can distinguish it from correlate_devices without opening either schema, since the repeat-check role is stated outright.

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 gives explicit when-to-use ('Use this for repeat checks') and routes the follow-up work precisely: 'only changed devices need a fresh correlate_devices call.' The sibling relationship and the condition that selects each tool are both spelled out.

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/idempotent/openWorld/non-destructive, and the description adds substantial value beyond them: the per-device return shape, prioritization order, result_hash retention, and explicit privacy handling (host/IP/MAC/user/site fields stripped and listed under 'privacy'). It also states an honesty contract ('never call an empty, unresolved or partial result clean') that no annotation conveys.

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 purpose is front-loaded in the first sentence and the return/policy details are dense rather than padded. It runs long and restates the honesty rule twice ('Report needs_review and partial coverage honestly' / 'never call ... clean'), and enumerates return fields in prose where less would do, but almost every sentence earns its place.

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, the description must carry return-value semantics, and it does: resolution outcome, coverage, warnings, needs_review, result_hash, fix plan, prioritized findings with range source and vendor advisories. Privacy constraints and next-tool usage are also covered, so an agent has everything needed to invoke and interpret it.

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 baseline is 3, but the description adds real meaning: vendor/product/version must be sent 'exactly as the inventory says,' no CPE is needed, and forbidden fields are stripped. The filters (max_findings, confirmed_only, etc.) are left to the schema, which documents them adequately.

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 (Find) plus the exact resource (CVEs affecting specific devices) and pins the scope to 'their exact firmware or software version.' This cleanly separates it from siblings like lookup_cve (single-CVE lookup) and get_fix_plan without needing to name them.

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?

'Use this for any specific device and firmware' gives a clear triggering context, and the note to keep result_hash 'for check_changes' routes the agent into the correct follow-up tool. It stops short of stating when NOT to use it (e.g. single-CVE questions belong to lookup_cve), so it is clear context rather than 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 already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description adds real behavioral value by disclosing that it reports plainly when a device did not resolve or coverage is partial, which the annotations cannot 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?

Purpose and returned content are front-loaded before the input guidance and privacy constraints. Two dense sentences, each carrying load, with no redundant 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?

With no output schema, the description carries the return-shape burden and does so by naming the fix groups and the two plan steps. Combined with annotations covering safety and a single well-documented parameter, this is nearly complete; only the when-to-use routing remains thin.

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%, so the baseline is 3. The description adds meaning on top by stressing exact-as-inventory matching and enumerating forbidden identifiers (host names, IP/MAC, user/site names), which sharpens correct usage beyond the schema's field descriptions.

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 resource and output ('Fix plan for one device') and details what the plan contains: fix groups mapping updates to CVEs, plus the known-exploited and full-coverage steps. This clearly separates it from lookup_cve (raw CVE data) though no sibling is named explicitly.

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?

Gives input-matching guidance ('send vendor, product and version exactly as the inventory says') and privacy exclusions, implying how to call it. But it never states when to reach for this tool versus correlate_devices or lookup_cve, so the when-to-use decision is left to inference.

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, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds value by disclosing that the record is 'trimmed' and listing the concrete fields returned (severity, CVSS, EPSS, fix status, advisories), which an agent cannot infer from the schema.

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, front-loaded with the lookup action and scope, followed by the sibling routing. No filler; every clause earns its place.

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, the description usefully enumerates return fields, which is the main gap it needs to fill. Auth/rate-limit behavior is not mentioned, but for a simple read-only lookup this is a minor omission.

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 single parameter is fully documented in the schema (100% coverage) with the same CVE-2024-9137 example, so the description adds little beyond it. Slight credit for reinforcing the ID format and clarifying that lookup is by CVE id only, not device.

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 ('Look up one CVE by id') with a concrete example (CVE-2024-9137), and enumerates the returned fields so the agent knows exactly what the record contains. It also explicitly distinguishes itself from the sibling correlate_devices.

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?

Gives the negative condition ('It is not device specific') and names the alternative tool with the condition that selects it ('to know whether a device is affected, use correlate_devices'). This is textbook routing guidance.

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