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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety bar is lower; the description still adds real value by scoping the tool's authority ('does not approve'). What it omits is more important: whether records are append-only/auditable, what `corrects` supersedes, and what evidence must exist before writing. The idempotency_key parameter also sits awkwardly against idempotentHint=false, and the description never clarifies retry behavior.

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, zero filler, and the core purpose is front-loaded before the exclusion. It is efficient, though the terseness is more a symptom of under-specification than of disciplined editing.

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 11-parameter, 10-required, nested-object, destructive write tool with no output schema needs substantially more explanation than two sentences. An agent cannot tell from the description what a valid call looks like, what the enum values mean, or how the recorded assessment relates to existing quality data.

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 only 9% (one of eleven parameters, idempotency_key, has any text), so the description carries the burden and largely fails. It never mentions company, scenarioId, runKind/runReference, outcome, notes, or the five-check nested `checks` object; the words 'evidence-backed' and 'correction' only faintly gesture at `checks.original_evidence` and `corrects`.

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 ('Record an evidence-backed assessment or correction'), which is far more informative than the tool name alone and matches the `kind`/`corrects` shape of the payload. It does not, however, differentiate itself from nearby siblings such as summer_quality_scenarios_save, summer_capability_checks_save, or summer_quality_corrections_list, so an agent must infer the boundary.

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?

'Does not approve a plan or customer action' gives one useful exclusion and implicitly distinguishes this from summer_actions_approve. But there is no positive when-to-use condition (when is an assessment required?), no prerequisites about gathering evidence first, and no named alternative for the opposite case.

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