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

Annotations already flag destructiveHint=true and idempotentHint=true, so the safety profile is covered; the description adds the non-obvious side effect that saving regenerates the closing report, plus the refusal rules and the 'closing always happens as of now' behavior. It stops short of saying whether the correction is audited or reversible, so it is not fully exhaustive, but it meaningfully exceeds the annotations.

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?

Purpose and the key exclusion are front-loaded, and each subsequent sentence carries distinct information (refusal rules, timestamp semantics, report regeneration). The 'like the pencil next to the closing date on the position screen' analogy and the slightly winding back-dating sentence cost it a little efficiency.

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 full schema coverage, no output schema, and annotations carrying the risk profile, the description covers preconditions, side effects and an alternative workflow. It leaves out permission/auth requirements and whether report regeneration is synchronous, which are minor residual gaps.

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 baseline is 3, and the description goes beyond it by adding validation meaning to closedAt ('a date later than today' is refused) and by clarifying that the stored date is corrected after the fact rather than driving the actual closure timestamp. It does not repeat the jobDescriptionId semantics, which is fine since the schema does.

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?

The description names a specific verb and resource ('Correct the closing date of a job position') and immediately bounds it to positions that are already closed, explicitly separating it from change_job_status which is the sibling that actually closes positions. An agent can identify the operation without reading 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?

It states when to use it (an already-closed position), when not to (open, paused or cancelled positions are refused), an input constraint (no date later than today), and the recommended alternative workflow for back-dated closures: close now, then correct the date. That is explicit routing plus an exclusion, which is the top of the scale.

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