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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description adds real value by disclosing the audit side effect ('both journals keep a line'), the authorization requirement (project members who may write only), and a plan-level availability gate. It does not cover failure modes or what happens when the two merged records have conflicting facts, which keeps it at 4 rather than 5.

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 in the first clause, and nearly every sentence carries operational information. The trailing constraints are written as telegraphic fragments ('Members of the project who may write only. Only where the company's plan includes AI.'), which saves space but costs a little readability.

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 one-parameter destructive mutation with no output schema, the description covers purpose, inversion target, id sourcing, consent, permissions, plan gating, and audit effects — enough to call it correctly. It omits error/edge-case behavior and any hint of the response, which is acceptable given no output schema exists but leaves a small gap.

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% and the single parameter is documented, so the baseline is 3. The description still earns credit by disambiguating which id to pass — the merged person's own id, not the surviving person's — and by pointing at list_persons as the way to find it, which prevents a plausible misuse.

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?

Opens with a specific verb-plus-resource framed as the inverse of a named sibling ('Undo merge_persons'), and clarifies the resulting state: the person becomes their own again with all spellings and facts. An agent can distinguish this from merge_persons, decide_persons, and delete_person without opening any schema.

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?

Gives clear preconditions: identify the person by their own id (as 'merged' appears in list_persons), ask the person first, the caller must be a project member with write access, and the company plan must include AI. It stops short of naming alternatives explicitly (e.g., delete_person or decide_persons when unmerging is not the intent), so it falls just below the top score.

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