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

Annotations only cover readOnlyHint/openWorldHint, but the description adds substantial behavioral context: the full state taxonomy and what each implies, the summary.shop no_channel_traffic guardrail (the problem is distribution, not titles/images), the warning that channel product ids are only unique within their own channel, and the caution about interpreting missing metrics. This is well beyond annotation coverage.

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, then the differentiating use case, then the state legend and guardrails. Every section is load-bearing, though the density and length (especially the inline state enumeration) is on the heavy side for a listing metrics tool.

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 compensates by explaining the state field's meaning, the summary.shop and coverage blocks, and the channel/store provenance of rows. An agent has enough to call the tool and interpret results correctly without further documentation.

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 the baseline is 3. The description adds real interpretive value on top: it explains that each row carries its channel and store and that these must be checked before comparing rows (because channel product ids are channel-scoped), which clarifies the provider/store filter semantics beyond their schema descriptions.

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?

Opens with a specific verb+resource: 'What the sales channel reports about each of your listings: impressions, clicks, click-through rate and units sold, plus a state.' It also explicitly distinguishes itself from the order-based analytics siblings by explaining that those cannot show see-but-don't-buy listings, so an agent can route 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 concrete when-to-use ('find listings people SEE but do not BUY'), when-not (order-based tools cannot show this), and sequencing rules ('READ `summary.shop` FIRST', 'ALWAYS check the coverage block before treating a missing metric as zero'). The state definitions double as action guidance (winner=scale, starved=needs discovery NOT a rewrite, dead=only state safe to archive).

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