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

Annotations only declare it is a non-read-only, non-destructive, non-idempotent write. The description adds genuinely new behavior: once added, the competitor's mentions and rankings are tracked alongside the brand's, which tells the agent about durable side effects. Retry semantics via requestId are also disclosed, though permission/auth requirements are not.

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?

Three compact sentences, front-loaded with the core action and effect, then the discovery hint, then the retry rule. No filler and nothing redundant with the schema.

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 an output schema present, return values need not be described, and the description covers the action, its tracking consequence, the alternative source of candidates, and retry behavior. The main remaining gap is the unmentioned organizationId and array-shape expectations.

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 only 17% (only requestId is documented inline), so the description has to compensate and partially does: it names the name, websiteDomains and brandNames payloads and ties the record to a project. organizationId is never explained and no format or cardinality guidance is given for the arrays.

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 and resource ('Add a competitor to a project') plus the three payload concepts it carries (website domains, brand names), and the verb cleanly separates it from update_competitor and delete_competitor. It also names discover_brands as the upstream proposal source, so the agent can place it in the workflow.

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?

Points at discover_brands as the tool that proposes competitors, giving real when-to-use context, and explains the retry condition for requestId. It stops short of an explicit exclusion (e.g. 'use update_competitor instead to change an existing one'), so it is clear context without full routing rules.

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