Diagnose a failure

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

With annotations providing only broad flags, the description adds meaningful behavioral detail: it records state in a bounded session and recommends rather than executes actions. This clarifies side effects and scope without contradicting the 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?

A single, tightly worded sentence front-loads the core verb and object, then packs in two meaningful behavioral outcomes. There is no filler or 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?

For a tool with seven optional but fully documented parameters and no output schema, the description conveys the essential flow: analyze, record, and recommend. It stops short of describing the exact shape of the recommendation output, but it is sufficiently complete for an agent to understand the tool's role.

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 100%, and the input schema already documents each parameter, so the tool description does not need to repeat parameter details. The description adds no parameter-specific meaning beyond the schema, so the baseline of 3 is appropriate.

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 a specific verb ('Analyze') and resource ('an error or failed operation'), and adds two concrete outcomes: recording in bounded session state and recommending safe next actions. It is clear about what the tool does, though it does not explicitly differentiate it from sibling tools like retry or fix_me.

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 phrase 'Analyze an error or failed operation' implies the intended trigger, and 'recommend safe next actions' positions it as an advisory step before acting. However, it gives no explicit guidance on when not to use it or how it compares to sibling alternatives.

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