Report Outcome — Did it work?

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

Annotations indicate readOnlyHint=false (write operation). The description adds valuable behavioral context: outcomes are recorded as expert reviews with scores (+1/-1), contributions grow shared operational memory, and passing certain fields triggers a structured execution_report. This goes beyond the basic annotation by explaining the system effect. A score of 5 might be warranted if it also mentioned authorization or idempotency, but the current disclosure is strong.

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 description is concise: three sentences plus a one-line note cover the core purpose, effect, and a key alternative. It front-loads the main action and uses formatting like 'ai-native:' to structure extra details. While slightly verbose with the 'EASIEST' emphasis, it avoids unnecessary repetition and earns a 4.

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?

The tool has 16 parameters, nested objects, and no output schema. The description gives a good overview of the main result (how reviews affect the network) and when to use optional fields, but it leaves many parameters unexplained, lacks details on return value or constraints (e.g., maxLength on notes is in schema, not described). For this complexity, the description is moderately complete but has gaps, justifying a 3.

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?

With schema description coverage at only 44%, many parameters (tool_calls, tokens_used, etc.) lack explanations in the schema. The description does not detail each parameter but highlights that task_type, stack, and errors_encountered are used for a structured execution_report. This adds some meaning beyond schema, but the agent must infer the purpose of many other parameters from their names alone. A score of 3 reflects partial compensation for low coverage.

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 description clearly states the tool's purpose: 'Report whether a recommended entity worked for your use case.' It specifies the verb ('report'), resource ('outcome'), and explicitly distinguishes from sibling 'nanmesh.trust.favor' by noting the agent_key requirement. The effect on the trust network (+1 for true, -1 for false) is also explained, making the purpose very specific and actionable.

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?

The description provides clear usage guidance: use this tool when you have an agent_key to report an outcome; if no key, use nanmesh.trust.favor instead. It also mentions that passing optional fields (task_type, stack, errors_encountered) leads to a structured execution_report, giving the agent a cue on when to include extra parameters. This effectively sets expectations and helps avoid misuse.

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