experience_update_achievement

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

Annotations only supply readOnlyHint=false, so the description carries the weight and does well: it discloses partial-update semantics ("Only the fields you pass change"), destructive list replacement for metrics/skills, and the immutable-provenance rule (agent_inferred stays agent_inferred and uncitable). It stops short of stating error behavior or whether a correction is reversible/logged.

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 purpose, then the partial-update rule, then the provenance caveat that prevents a common misuse. Four sentences, each carrying a distinct decision-relevant fact, with no redundancy.

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 6-parameter mutation tool with only readOnlyHint=false for annotations and no output schema, the description covers the remaining gaps: what changes, what is destroyed, and what stays fixed. Nothing an agent needs 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 adds real signal by stressing that metrics and skills REPLACE wholesale rather than merge, which is the riskiest parameter behavior. It does not clarify employment_id as a move operation beyond what the schema already says.

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?

Specific verb+resource: "Correct an achievement already in the bank," with an immediate distinction from the add path ("cannot be fixed by re-adding it"). An agent can tell this apart from experience_add_achievement and experience_update_employment without inspecting schemas.

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?

Names the primary trigger (a typo in the claim), rules out the tempting alternative (re-adding), and spells out the only valid path to change citation status (confirm with the candidate, then record what they said). This is explicit when/when-not/alternative guidance.

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