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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds crucial non-obvious behavior: figures are comparable only within a panel version, one-step movements are likely noise (with historical context on prompt runs), data is re-measured weekly so results remain stable until the next release, and licensing/attribution is disclosed. This far exceeds the annotation-provided safety profile.

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?

The description is front-loaded with a one-sentence summary of the tool's output, followed by when-to-use, caveats, and licensing. Although it is a multi-paragraph text, every sentence adds unique value—no filler, repetition, or ambiguity. The structure helps the agent quickly grasp the core function and then dive into interpretation constraints.

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?

The tool has no parameters and an output schema exists, so the description's role is to provide interpretation context—and it does that thoroughly. It covers panel version comparability, noise thresholds, step-size reference, current-release alternative, weekly re-measurement, and attribution requirements. Nothing critical is missing for correct use.

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?

The input schema has zero properties, so no parameter descriptions are needed. The description confirms the tool returns the full series without filtering ('Every DABLOCK release ever published, as a series per brand'), which aligns with the empty schema. Baseline for zero params is 4, and no additional meaning is missing.

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 opens with a precise definition: 'Every DABLOCK release ever published, as a series per brand: share of answer at each weekly measurement with the date and panel version it was taken under.' It clearly identifies the tool as a historical time-series retrieval per brand and distinguishes it from siblings by directing to get_visibility_index for the current release and get_methodology for step size.

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?

Explicit usage guidance is provided: 'Use this for any question about change — is a brand rising, when did it enter the index, how volatile is the category.' It also names alternatives: 'For the current release alone use get_visibility_index' and 'Call get_methodology for the exact step size.' This makes the decision boundary crisp.

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