analyze_failures

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

Annotations are negative (readOnlyHint false, destructiveHint false), so they do not fully characterize side effects. The description adds some behavioral color by specifying deterministic output and optional host-model hypotheses, but it does not disclose persistence, mutation, or invocation side effects beyond that.

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 front-loaded sentence with a clear verb and no filler words. It is concise and readable, though the jargon ('deterministic issues', 'host hypotheses') is dense and would benefit from a short expansion.

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?

With an output schema, 100% parameter description coverage, and simple Boolean/string parameters, the definition is minimally sufficient for invoking the tool. However, it lacks usage context, prerequisites beyond schema hints, and behavioral detail, so an agent may not know precisely when to call it or what side effects to expect.

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%, so both diagnosis_id and use_sampling are already documented in the schema; the tool description adds no parameter-level meaning. Baseline of 3 applies because the schema carries the full burden.

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 action ('Build') and concrete outputs ('deterministic issues' and 'optional host hypotheses') scoped to 'known evidence IDs', so the tool's purpose is clear and distinct from sibling tools like list_diagnoses or execute_probe. It stops short of a 5 because 'known evidence IDs' is undefined and no sibling is explicitly contrasted.

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: the schema notes diagnosis_id comes from start_diagnosis, which suggests ordering, but the description never says when to choose analyze_failures over get_diagnosis, discover_profile, or build_runbook_report. There are no exclusions, conditions, or alternative tool mentions.

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