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

With no annotations, the description carries the full burden and does so: it names the refusal error code, lists the exact blocking conditions, discloses authorization constraints (agents, keys and office staff cannot override), and notes overrides are recorded and audited. That is far more than a restatement of the schema.

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 action and actor, then the refusal logic. The middle sentence is long and clause-heavy, but each clause specifies a distinct blocking condition rather than padding.

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 two-parameter mutation with an output schema and no annotations, the definition covers authorization, failure conditions, override mechanics and audit consequences. Repeating return values is unnecessary given the output schema.

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 50% (job_id undocumented), but the description adds real meaning for override_reason that the schema does not: it is owner-only, available solely via the hosted override page, and is audited. job_id remains self-evident from the name and format.

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?

'Mark a job done' is a specific verb+resource, and the parenthetical '(owner or office)' scopes the actor. It is clearly distinct from the sibling visits_done, though it never names that sibling explicitly.

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?

It spells out exactly when the call is refused (checklist_open with three enumerated conditions) and the only alternative path — the owner passing override_reason on the hosted override page. It also states plainly who cannot use the override, which steers agents away from a dead end.

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