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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description is consistent with them ('Reading candidate metadata does not write statistics'). It adds genuinely non-schema context (fixed observed output shape, no documentation review, untested vendor integrations, no historical/batch queries), but the sentences are cryptic and the 'not-collected with null counts' claim is never reconciled with the tool's apparent reporting purpose.

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?

Six dense, jargon-laden sentences ('Complete declarations appear once in interfaces; matched/guide entries are explicit local references') that are not front-loaded and bury any actionable meaning. Space is spent on tangential claims rather than the tool's core contract.

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 explain what comes back, and it only says results are 'not-collected with null usage counts' — an ambiguous, possibly misleading return claim. It omits what a 'usage observation' is, its units, and how the days/language/locale inputs shape output, leaving the contract incomplete for a 4-param tool.

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?

Three of four parameters (locale, language, softwareId) carry their own schema descriptions, giving ~75% coverage, so the schema does the heavy lifting. The description adds nothing about the undocumented `days` window, the retained 'current observation' scope, or how locale/language interact with the output, so it does not compensate for the gap.

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 never states plainly what the tool does (e.g. 'returns usage observations for a selected candidate software'). Its lead sentence, 'This selected candidate set has no actual-use evidence. Return not-collected with null usage counts,' reads as an instruction about a degenerate outcome rather than a purpose statement, and is at odds with the resource implied by the name and the get_usage_observations sibling.

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?

Only fragments of guidance appear: 'Only the retained current observation is available; historical batch queries are not accepted.' There is no statement of when to use this tool versus the 15 siblings (e.g. candidate_get_software, get_usage_observations), nor prerequisites such as needing a softwareId from the selected Registry set.

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