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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds substantial context: it reveals that only fields returned by the tool are verified and imposes a data accuracy contract (do not invent missing values, label derived metrics, say unavailable when missing). This goes beyond the annotations and shapes how the agent should treat results.

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 front-loaded with its action and purpose, and the first two sentences are concise. The third sentence is a verbose data-accuracy contract that, while valuable, could be condensed or split for readability. Overall it earns its place but is slightly wordy.

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 output schema, the description explicitly enumerates the returned elements (expression DSL, variables dict, cross_source_checks list, metadata). It covers selection, usage context, response formatting, and data accuracy rules—everything an agent needs for correct invocation and result handling.

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 only parameter, 'key', is already described in the schema with an example ('mrr', 'aov') and 100% coverage. The description's reference to 'by key' adds no further semantic detail; the baseline of 3 applies because the schema does the heavy lifting.

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 opens with 'Fetch one metric spec by key', which is a specific verb, resource, and scope. It enumerates the return contents and clearly distinguishes the tool from metric_spec_resolve and metric_spec_list, leaving no ambiguity about what it does.

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?

It explicitly states when to use this tool: 'Use before metric_spec_resolve when the user wants to see HOW a number is computed, not just the value.' This names the sibling and defines the selection criterion. It also instructs how to format responses, which is direct usage guidance.

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