audit_orphan_files

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

With readOnlyHint=true already in annotations, the description adds real value by reinforcing 'Ne supprime rien' and disclosing the heuristics used (age, job association, temp-file extensions). It omits any note on result ordering, limits, or cost, but the output schema covers the return shape.

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?

Three short sentences, front-loaded with the identification criteria and the safety assurance, with the usage trigger last. No padding, though the criteria list is slightly dense.

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 read-only audit tool with an output schema and read-only annotation, the description supplies the heuristics and the trigger. The remaining gap is parameter meaning, which is unaddressed in both schema and description.

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 description coverage is 0% for 4 parameters. The description loosely implies them ('volumineux' → min_size_mb, 'anciens' → days, 'sous le scratch' → path) but never explains top, defaults, or units, so a caller still has to guess from the schema titles.

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?

It states a specific verb (Repere/identifies) and resource (large abandoned files under scratch) and spells out the detection criteria: old, no active associated job, or typical temp compute files (.rwf, .scr, .tmp). It also plainly distinguishes itself from the delete-action siblings by declaring 'Ne supprime rien'.

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 gives an explicit trigger condition: 'Utile quand romeo_quota signale un depassement', naming the sibling that signals the need. It does not say when NOT to use it or mention storage_cleanup_helper as the alternative for the actual cleanup, so it stops short of full routing guidance.

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