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

Annotations already declare the tool is not read-only, is idempotent, and non-destructive; the description goes further by specifying the outcome ('moves the claim to manual review'), that the tester result is not deleted, and that no money transfers. This adds useful context beyond the annotation flags, though the underlying review process after the dispute is not described.

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?

Four compact sentences, with the main action and eligibility in the first sentence followed by constraints and side effects. No filler or duplicated schema details; every sentence earns its place.

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 four-parameter mutation tool with no output schema, the description covers role, valid grounds, availability window, outcome, and side effects. It lacks explicit parameter mapping, but the schema's patterns and the agent_key description fill most remaining 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 description coverage is only 25%, so the description carries much of the burden. It indirectly explains confirm_run_did_not_occur via 'only when the stated run did not take place' and constrains what reason content is invalid, but it never maps these conditions to the actual parameter names and says nothing explicit about claim_id.

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?

Description opens with a specific verb and resource ('dispute a funded field-test result claim') and narrows scope with an eligibility condition ('only when the stated run did not take place'). The 'As the tested service provider' role also separates it from sibling dispute tools like speedbot_exchange_funded_task_dispute.

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?

States clear when-to-use conditions (run did not occur, within 72 hours, no confirmation recorded) and an explicit when-not ('Disagreeing with a failed outcome is not grounds for a dispute'). It does not name an alternative tool for the exclusion, so it stops short of fully routing between siblings.

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