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

Annotations only say readOnlyHint=false with openWorldHint=true; the description explains exactly what that mutation covers – local accounting only, never submits jobs or spends new credits – and how unknown submissions stay conservatively reserved pending operator evidence. That is precisely the context the annotations cannot convey.

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 trigger and scope, then constraints. Dense but each sentence carries information; only a minor typo ('up to50') and slight repetition of the no-arguments point against perfect structure.

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 supplies the return shape (checked, errors, unknown_submissions counts) and the safety envelope for a mutating-but-local tool. Nothing an agent needs before calling is absent.

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?

Zero parameters, so the baseline is 4; the description reinforces this with 'Takes no arguments' and notes company/permissions come from the authenticated connection. No additional syntax is needed or missing.

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 (refresh) and resource (local credit accounting from upstream states) with an explicit scope limit of up to 50 tracked nonterminal jobs with known IDs. It immediately distinguishes itself from skavio_get_job by name, so an agent can route 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?

Gives an explicit trigger ('when an adapter reservation appears stale') and names the alternative for the adjacent case ('use skavio_get_job for a specific known job'). It also states an exclusion: a nonzero unknown count is not permission to create a new idempotency key.

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