mkt_metric_measure

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

With no annotations, the description at least discloses that the operation is read-only and deterministic, and it states the zero-denominator policy (return null rather than fabricate a result) — genuinely useful behavioral context. It stops short of covering behavior for an unknown metric_id, a version mismatch, or malformed events, which matter for a computation 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?

A single tight sentence with the read-only qualifier and the computation contract front-loaded, plus a semicolon-delimited edge-case clause. Nothing is redundant, though the density leaves the parameter surface untouched.

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 six-parameter tool with a nested object, no annotations, no output schema, and zero schema description coverage, the definition is under-specified. It establishes intent and one edge case but leaves the agent guessing about scope, time windowing, cohort semantics, and the return shape beyond the null case.

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 0% across six parameters including a nested events array, so the description carries the full burden — yet it only alludes to events and a versioned metric dictionary. as_of, scope, and cohort_end are never explained, and the element shape of events is entirely undocumented anywhere.

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 names a specific verb and resource: deterministic KPI computation against a versioned metric dictionary over supplied events. That is far more precise than the bare tool name, though it never contrasts itself with plausible siblings such as mkt_scorecard or mkt_progress, so an agent must infer the boundary.

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 implies the caller must supply events and a metric identity, but there is no stated when-to-use, when-not-to-use, or named alternative among the many mkt_* siblings. An agent choosing between this and mkt_scorecard or mkt_progress gets no routing help.

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