mkt_revise

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

No annotations are supplied, so the description carries the full disclosure burden. It does usefully establish that the operation is read-only and that it will decline to conclude on small samples, but it says nothing about required permissions, what the returned recommendation looks like structurally, or what happens when the supplied data is malformed.

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 compact sentence that front-loads the most decision-relevant fact (read-only) and then the output shape. No wasted wording, though brevity here partly reflects under-specification rather than efficiency.

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?

Two opaque nested-object inputs, no annotations, no output schema, and no param documentation — the description should explain the input contract and does not. For a tool whose entire value is a precisely formatted before/after recommendation, the definition is too thin for an agent to invoke it 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 description coverage is 0% and both parameters are untyped nested objects, so the description must compensate and does not. It never explains that 'params' presumably carries the current parameter set and 'result' the measured outcomes, nor what keys those objects expect.

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 states the tool produces a recommendation of 'which parameter, from what value to what value' and tags it parameter-level or strategy-level, plus that it is read-only feedback. That is a recognizable advisory function, but the object being revised is left abstract ('参数' of what?) and no distinction from siblings such as mkt_optimize or mkt_scorecard is drawn.

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?

There is no statement of when to call this versus mkt_optimize, mkt_scorecard, or mkt_result. The only conditional mentioned — refusing to conclude when the sample is insufficient — is a behavior of the tool, not guidance on when an agent should select it.

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