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

Annotations already declare a safe, idempotent, read-only operation, so the bar is lower. The description adds real behavioral context beyond that: the exact fields each entry carries, the response post-processing obligation (attribution footer handling), and a data accuracy contract governing what counts as verified. The trailing accuracy contract is somewhat generic boilerplate rather than tool-specific behavior, which keeps this from a 5.

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 purpose and usage routing are front-loaded and efficient, but a large trailing block of generic accuracy-contract language (budgets, ROAS, CPA, 'waste' labels) is not specific to listing metric specs and dilutes focus. The response is longer than the tool's core task warrants.

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?

There is no output schema, so the description correctly compensates by enumerating the returned fields (spec key, label, expected_unit, expression, version) and covering both optional filters. Combined with the read-only annotations, an agent has what it needs to call and consume this tool, though pagination or empty-result behavior is unaddressed.

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 filters (unit, owner_email) are already fully documented in the schema. The description adds no filter syntax, format, or default detail beyond what structured data provides. Baseline 3 applies when the schema does all the parameter work.

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 a specific verb and resource ('List the user's declared metric specs') and grounds them with concrete examples (MRR, AOV, monthly_active_customers). It also previews the returned fields, so an agent knows exactly what this tool surfaces. The 'List' verb distinguishes it from the singular metric_spec_get sibling.

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 gives an explicit when ('BEFORE computing any KPI from raw connector data') and names the alternative tool and condition that selects it ('if a spec exists for the question, call metric_spec_resolve instead of rolling your own aggregate'). This is a textbook routing instruction with no inference required.

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