Save the person's application answers

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

Annotations already flag destructiveHint=true/readOnly=false, and the description meaningfully extends them: it explains the replace-vs-merge semantics, that an empty answer set can finish onboarding, that readiness is rechecked, and critically that no application is sent. That last point usefully bounds the blast radius of a destructive-classified tool.

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?

Dense and front-loaded – the core action leads, followed by flag semantics, replacement behavior, the empty-set edge case, and the return contract. No filler sentences, though the single unbroken paragraph is dense to parse.

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 destructive, deeply nested, 3-param tool with an output schema, the description covers the operation's scope, side-effect boundary, edge case, and return fields (ready/stillMissing) without re-explaining the schema. Only the contact-group parameter semantics remain unaddressed.

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 33%, so the description must carry load. It does add the literal meaning of the required statedByPerson:true flag and the replace semantics of eligibility.countries, but says nothing about the contact group fields or how the nested answer groups are validated. Partial compensation, not full.

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 ('Saves person-stated application-answer and contact groups') and describes the downstream effect (validation, readiness recheck, setup completion). It is distinguishable from siblings like edit_answer and update_profile, though it never names an alternative to route against.

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 rather than stated: the reader infers this is the write path for onboarding answers and that an empty set is legal, but there is no explicit when-to-use versus edit_answer or update_profile, and no stated prerequisites or exclusions.

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