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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial extra behavior: only disagreeing specs are returned, an empty list is normal, an attribution footer must be echoed verbatim, and a data-accuracy contract governs invented vs. derived values. That is far beyond what the structured fields convey.

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 core purpose and empty-result semantics are front-loaded in the first two sentences, which is good. The trailing footer and data-accuracy boilerplate is longer and more generic, diluting conciseness slightly, but each block does carry operative instruction.

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 no input parameters, no output schema, and rich annotations, the description covers everything an agent needs: what is scanned, what is returned, what an empty list means, and how to handle an attribution footer. Nothing material is missing.

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?

The tool takes zero parameters, so there is nothing for the description to clarify; baseline for a no-param tool is 4. No parameter semantics are needed or missing.

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 resource ('walk every metric spec ... resolve each one and its comparison') and a precise scope condition (non-empty cross_source_checks, disagreement beyond tolerance_percent). It is clearly distinguishable from siblings like metric_spec_resolve and metric_spec_list, which operate on single specs or list 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?

Provides clear context for when to reach for this tool ('what's silently disagreeing in my numbers' dashboard) and clarifies the empty-result case is a green signal rather than an error. It does not explicitly name an alternative tool or state when NOT to use it, so it falls short of a 5.

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