analyze_failure

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: output is 'sanitized' (privacy handling) and 'deterministic' (no model inference), which shapes what the agent should expect. It omits latency, response shape, and the openWorldHint implication.

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 compact sentence with zero waste; the output nature is front-loaded and the constraint ('no AI root-cause claim') is appended where it belongs. Nothing redundant with the name or annotations.

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?

One simple required parameter, no output schema, and rich annotations mean the description's burden is light, and it does explain the deliverable (evidence + investigation areas, not a diagnosis). It would be stronger if it hinted at the structure of 'investigation areas' or where the messageId comes from.

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 never mentions messageId, its format, or where to obtain it. The schema constrains the value (pattern, maxLength 256) but does not explain what a messageId refers to, so the description fails to compensate for the coverage gap.

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?

States a specific verb+resource: it gathers 'sanitized diagnostic evidence and deterministic investigation areas' rather than making a root-cause claim. This is clearly different from the sibling reads like get_error_details or get_recent_failures, though no sibling is named. The phrase 'deterministic investigation areas' is slightly abstract but still conveys a distinct output goal.

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?

Usage is only implied: an agent infers this is the tool you call on a failure message when you want evidence rather than a diagnosis. No alternatives (get_error_details, get_recent_failures) are named and no conditions or prerequisites are given. The 'no AI root-cause claim' note functions as a when-not, which is why this is not a 2.

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