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

Annotations already cover the safety profile (read-only, closed-world, non-destructive), and the description adds genuinely useful behavioral context on top: the data is a snapshot of the latest collection day rather than a time series, and each metric field carries its own unit scale. That unit information prevents the agent from misreading values. It says nothing about how ties are broken, whether the brand is always included, or a confidence caveat.

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 compact sentences plus a quoted intent, with the scope statement front-loaded before the metric semantics and the usage cue last. There is essentially no filler.

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 does the return-value work by naming the ranking fields and their scales, and it establishes the temporal scope, which is what an agent most needs. The remaining gap is what the rows actually look like (brand identifiers, whether the workspace brand is flagged) and how limit interacts with the result set.

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 67%, with market and metric already documented inline, so the schema does the baseline work. The description earns above baseline by explaining what the metric values mean at the ranges of sovPercentage, mentionRate, citationRate, and avgSentiment, which the enum alone does not convey. It says nothing about limit, leaving pagination/top-N behavior undocumented in both places.

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 a specific resource and scope: a competitor leaderboard for the latest collection day, covering the workspace brand and its competitors ranked by a chosen metric. An agent can tell this apart from get_evidence or get_source_gaps. It does not explicitly contrast with get_visibility_summary, which is the nearest neighbor, so it stops short of a 5.

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?

It gives a clear triggering intent, quoted as "where do we rank / who is ahead of us", which is enough to pick this tool for a ranking question. It offers no when-not guidance and names no alternative sibling for overlapping visibility questions, so the agent must infer the boundary itself.

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