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

Annotations only declare readOnlyHint/openWorldHint; the description adds substantial context beyond them — verdicts are auto-computed per kind on the single metric the change should move, `unmeasurable` is the default rather than an error, `confounded` means overlapping changes, and verdicts settle at read time. These are non-obvious behaviors an agent could not infer from the annotations.

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-loaded with the core purpose and the sibling contrast, and most sentences carry real interpretive value. It is somewhat long and ends with a stray artifact token ('[#a02f68]') that serves no purpose.

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 read-only analytics tool with no output schema, the description covers the domain concepts an agent needs (verdict taxonomy, verdict_reason values, settling behavior) thoroughly enough that no essential context is missing.

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%, so all six filters are already documented in the schema; the description adds almost no per-parameter syntax or format detail. It only indirectly touches `days` via the 'finalised enough days either side' remark, so the baseline of 3 is 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+resource — what changed on your listings and whether the change worked — and explicitly frames itself against the sibling channel_performance ('that says what to fix, this says whether the last fix landed'). An agent can distinguish it from channel_performance without opening either 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?

Names the alternative (channel_performance) and the condition that separates them, then gives explicit interpretive guidance: read `verdict_reason` before saying anything, treat `unmeasurable` as normal, and don't attribute `confounded` to the most recent change. This is close to a full when-to-use/when-not-to-use contract.

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