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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description goes well beyond that: caller authorization (payer only), lifecycle precondition (job must be held), fee withholding semantics (ESCROW_FEE_BPS recorded on job, credited to nobody), and duplicate/after-refund rejection behavior with no credit movement.

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 purpose, then authorization, then fee mechanics, then failure modes, then the REST mapping. Every sentence carries a distinct fact and nothing is repeated from the schema.

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 tool with no output schema, the description covers permissions, preconditions, credit math, idempotency, and error outcomes — everything an agent needs to invoke it correctly and predict the effect.

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 100% and both parameters are documented there (job_id format, api_key fallback behavior). The description adds no parameter-level detail beyond incidental mentions of amount_credits and the ESCROW_FEE_BPS config value, so the baseline of 3 applies.

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 (release held escrow credits to the payee) plus the triggering condition (work delivered). It is clearly separable from siblings like refund_job and get_job without opening any 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 concrete when/when-not conditions: only the payer may release, only while the job is held, and release after a refund or a second release is rejected. It stops short of explicitly naming refund_job as the alternative path, so it is strong context rather than full routing.

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