analyze_failures

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'read-only' mostly restates structured data. The description adds useful context about ordering after list_runs discovery, but it does not clarify how a failure cohort is determined or what happens when the filter is omitted.

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 one tightly front-loaded sentence covering action, target, mode, and workflow placement. Every phrase carries intent, and there is no filler.

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?

Despite the output schema, the description leaves critical invocation details unstated: how to construct the 'explicit filtered failure cohort,' whether filter may be omitted, and which statuses count as failures. For a tool with a large nested RunFilter and zero parameter documentation, this is a significant gap.

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%, so the description must compensate, but it only hints at the filter via 'explicit filtered failure cohort' and says nothing about the required 'limit' parameter. The large RunFilter object's fields are left unexplained, forcing the agent to infer semantics from enum names like 'failed' and 'timed_out'.

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 states a specific action ('Analyze'), a resource ('failure cohort'), and a workflow position ('after list_runs discovery'), making the tool's purpose clear. It does not explicitly contrast it with sibling analyze_* tools, but the 'failures' scoping provides enough differentiation.

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?

'After list_runs discovery' gives an explicit sequencing cue, and 'read-only' tells the agent this is a post-discovery analysis operation. It lacks explicit exclusions or named alternatives, but the context is clear enough for an agent to know when to invoke it.

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