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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the description is free to add the value beyond that: the artifact is externally shareable, gets a link, and has a branding prerequisite with a stated failure mode. It does not mention that repeated calls likely create duplicate reports, but the non-idempotent hint already flags that.

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?

Two sentences, no filler. The action and output are front-loaded, and the prerequisite follows. The branding sentence carries real operational weight rather than padding.

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?

There is no output schema, and the description compensates by stating the return value (a link). Required inputs and the branding prerequisite are covered, making the tool callable without guessing. Minor gaps remain around what happens on re-invocation and how the client value must match list_clients.

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 75%, so most parameters are documented in the schema. The description adds meaning for the 'sections' payload by telling the agent to write the commentary itself in plain client language, but it does not clarify title/period_label semantics beyond what the schema already provides. Baseline 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 ('Build a shareable, agency-branded report for a client') and its output ('return its link'), which distinguishes it from the data-pull siblings ads_report and ga4_report. It does not explicitly name those siblings as alternatives, but the resource is distinct enough for an agent to disambiguate.

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 real context for when to use it: the agent must author sections itself from data already pulled, and branding must be configured at /dashboard first or the report goes out unbranded. The dependency is stated clearly, though no sibling tool is named as the source of that data.

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