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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: rules are deterministic, the explanation is written from the cited record with a model fallback to the record's own text, output includes citations and exactly one next step, and it explicitly never rates an arrangement as safe. That last constraint is a valuable disclosure an agent could not 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?

Front-loaded with the core action and the two input modes, and the closing example earns its place by making the abstract shape concrete. Some sentences are long and clause-heavy ('The explanation is written from the cited record, by the model when available and from the record's own text otherwise'), but there is little outright waste.

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 spelled out, yet the description still summarizes them (citations plus one next step). For a tool with nested, undocumented parameters, it covers the two input shapes and the safety stance adequately. The main residual gap is the posture field semantics, which neither schema nor description explains.

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% across three parameters including two nested objects, so the description must carry the load. It does explain the two mutually exclusive modes (answers vs posture) and gives a concrete example payload for the readiness case, which clarifies devicesLocation/recoveryKnown. It does not explain the posture fields, the playbookId default, or the yes/no/unsure semantics, leaving real gaps.

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: it reads validated answers and names the gap via deterministic rules, adding the layer for posture. It also distinguishes itself from check_security_posture by noting the posture input is 'the same shape check_security_posture takes', which signals a different role. The prose is dense but an agent can tell what it produces (an explanation with citations and one next step).

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 when to use it (when you have validated readiness or posture answers and want a gap explained) and points at check_security_posture as the source of the posture shape. However, it never explicitly says when to choose this over check_security_posture or assess_risk, nor what prerequisites (validated answers) must exist first. Usage is inferable rather than stated.

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