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

Beyond the annotations (readOnlyHint=false, openWorldHint=false, idempotentHint=false), the description discloses genuinely operational facts: terms stay TBD and are not guaranteed until accepted, pay runs over a specific PayPal site-order rail with ST- codes, free is discretionary with a typical use pattern, and the feature is staged flag-off. These are exactly the traits an agent cannot derive from the schema or 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?

The WHEN clause is front-loaded and the middle sentences are dense with useful rules rather than filler. The trailing "Example: barter_code_offer {}" carries little value since all parameters are optional and the schema already shows the shape, but it is a minor cost in an otherwise efficient definition.

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 mutation tool with no output schema, the description covers sequencing, path semantics, and the non-guaranteed nature of proposals, which is close to sufficient. What it omits is what a successful proposal returns (an id? a status?), whether a proposal can be revised or withdrawn, and any rate or concurrency limits on repeated offers.

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 the baseline would be 3, but the description adds real meaning to the path enum — explaining what pay (PayPal ST- rail, post-acceptance), barter (give something of value: rentals, promotion, skills, referrals, or own work), and free (discretionary request) actually commit the caller to. That is semantic content the enum labels alone do not convey; offer_usd's tier-range constraint is merely restated.

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 opening sentence gives a specific verb and resource ("Propose coding-job terms") and the WHEN clause anchors it to a job_id produced by barter_code_scope, which separates it from siblings like barter_code_accept or barter_code_status. The three settlement paths (pay, barter, free) further sharpen what this tool does versus the surrounding workflow tools.

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 entry condition ("you have a job_id from barter_code_scope") and describes each path's rules, including that pay only applies after Perry or Rock accepts. It stops short of saying when not to use it — e.g., that terms should not be re-proposed after acceptance or that barter_code_accept is the follow-up step — so the routing is clear but not exhaustive.

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