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

Goes well beyond the annotations: enumerates the returned artifacts (live value, spec version, source-call ledger with dispatched tools and row counts, no persisted row data, drift vs cross_source_checks, validation warnings, provenance footer) and explicitly declares 'Result is NEVER cached; each call fires fresh dispatch'. This is unusually rich behavioral disclosure for a read-only tool.

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?

Front-loads purpose and return contents before the usage trigger, which is the right ordering. The long data-accuracy/attribution contract paragraph is dense but each clause maps to a real behavioral constraint, so it earns most of its length; a slightly tighter phrasing would make it a 5.

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 fully carries the burden of describing return values and does so item by item, plus adds response-formatting and data-accuracy contracts. An agent has everything needed to call it and interpret the result correctly.

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 100% for the single 'key' parameter, so the schema already documents everything (including the 'mrr' example). The description adds no syntax, format, or lookup guidance beyond what the schema provides, making the baseline 3 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 resource with scope: 'Compute a metric spec NOW' and 'Returns the live value, the spec version'. The emphasis on live computation and fresh dispatch implicitly distinguishes it from siblings like metric_spec_get and metric_spec_list, so an agent can tell what it is without opening a schema.

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?

Gives a clear usage trigger: 'call it whenever the user asks "what is our <metric>?" and a spec exists for it', plus the 'hot path' framing. It does not explicitly name alternatives (e.g. metric_spec_get) or state when NOT to use it, so it stops short of full routing guidance.

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