get_reputation

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

With no annotations provided, the description carries the full burden. It excels by disclosing that the tool always returns honesty caveats, explaining that feedback is self-reported and a weak signal, especially for low counts. This provides valuable behavioral context beyond a simple 'read' action.

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 appropriately concise: two sentences that front-load the core function and add a critical caveat. Every sentence provides value without redundancy.

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 description provides a solid overview for a read-only tool with no output schema. It covers the main capability and an important caveat. However, it omits details about pagination behavior (limit/offset) and the exact structure of the summary, which would be helpful given no output schema.

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?

The input schema has only 20% coverage (only chain has a description). The description adds meaning for includeRaw ('raw feedback entries') and clarifies the context of agentId ('an agent's'). However, it does not discuss limit/offset pagination semantics, leaving some parameters underdefined.

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: reading an agent's Reputation Registry feedback summary, optionally including raw entries. It uses a specific verb ('Reads') and resource ('Reputation Registry feedback summary'), distinguishing it from siblings like get_validations and assess_trust.

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 implies the tool is used for reading reputation feedback but does not explicitly state when to use this tool over alternatives or mention any exclusions. It lacks direct guidance on choosing between this and related tools like get_validations or assess_trust.

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