AgentRescue

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

With no annotations, the description carries the disclosure burden and does well: advisory-only, never executes fixes, no charge, paid trial disabled, and a hard privacy constraint against credentials or personal data. It does not mention rate limits, latency, or what an evidence-linked response looks like beyond that phrase, so it is strong but not exhaustive.

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 sentences, each doing work, with the usage trigger front-loaded before the behavioral and privacy constraints. The billing sentence ('No charge; the x402 paid trial is disabled') is the weakest line but is defensible cost context an agent may need.

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?

An output schema exists, so return values needn't be spelled out, and the description still characterizes them as advisory and evidence-linked. Privacy and no-side-effect behavior are covered. The remaining gap is input format guidance for the two undocumented parameters.

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 0%, and the description compensates partially: 'error' is scoped to the sanitized error from the latest request, and 'system' to the originating system. However, it never says what error format is expected (raw body, message, stack trace) or what values 'system' accepts beyond the default of mcp, leaving real ambiguity.

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 names the resource (a failed HTTP/API/MCP request) and the output (advisory, evidence-linked recovery steps), and explicitly says it never executes fixes. It is clear what the tool produces. It loses a point only because no sibling tools exist to differentiate against, so nothing sharpens the boundary.

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 explicit triggers: after an HTTP/API/MCP request fails, or when transport succeeds but the expected result is missing or incorrect. It further scopes the input to 'only the sanitized error from the latest request and its system', which tells the agent exactly what state to capture. Nothing is left to inference.

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