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

Annotations already declare this is a non-read-only, open-world, non-idempotent, non-destructive mutation, so the safety profile is covered. The description adds real behavioral context beyond them: the consent requirement ('Only on the person's word'), the fact that specifying a company pulls the whole company back, and the presence of a human-readable `say` field. It does not address what happens when nothing is supplied or what a second identical restore does, despite idempotentHint=false.

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 short, front-loaded sentences with no filler, and the consent condition is placed before the output note. The middle clause ('with whole_company, or a company alone, the company comes back too') is telegraphic and slightly awkward to parse, which costs a point.

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?

With no output schema, the description still points at the `say` summary field, which is the key return detail. The main coverage gap is that all five parameters are optional and the description never says what a bare call does or which identifier takes precedence when several are sent.

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 individual parameter meanings are already documented and baseline would be 3. The description goes beyond that by defining the interaction between parameters: key vs. job_id vs. title+company as alternative identifiers, and company used alone or with whole_company to expand the restore scope.

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+resource pair ('Put a dismissed match back') and extends it to a second object ('or a ruled-out company'). It also names the sibling that produces the input key (list_dismissed), so the agent can distinguish restoration from listing without opening either 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?

Explains where the input comes from (the key from list_dismissed) and gives the required precondition 'Only on the person's word', which is effectively a when-to-use gate. It does not name the inverse operation (hide_match) as a contrast, so the alternative path is only implicit.

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