diagnose_plugin_failure

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

Annotations only declare readOnly/non-destructive; the description adds substantial behavioral context beyond them: that missing, forbidden, and limited sources are reported, that root cause is deliberately left undetermined, that current step state is not historical config, that include_text opts into business data with secure columns never selected, and that bounded reads report incompleteness.

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?

Two dense sentences, front-loaded with the core action and source list, with caveats packed at the end. Efficient for a 17-parameter tool, though the warnings are terse to the point of being easy to skim past.

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 complex, no-output-schema tool the description covers the sources, anchoring, safety, and limits well. It does not describe the resulting report's sections or how the sources are correlated, which would help an agent interpret results, but the essentials are present.

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 coverage is 82%, so most parameters are documented in the schema itself. The description adds the semantic of the anchoring keys (correlation, step, plugin type) but says nothing about top, max_pages, from_time/to_time defaults beyond what the schema already states; baseline 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?

States a specific verb and deliverable ('build a read-only evidence report') and names the three data sources (exception-filtered traces, failed jobs, current plugin steps) plus the anchoring keys. It implicitly distinguishes itself from single-source siblings like query_plugin_trace_logs and query_failed_system_jobs by being a composite, though it never names them.

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 context ('anchored by correlation, step or plugin type') and the caveat 'Current step state is not historical configuration' imply a diagnostic/forensic use case, but there is no explicit when-to-use or when-to-prefer-sibling guidance despite many adjacent query tools. Usage must be inferred.

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