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

Annotations already flag destructiveHint=true, so the description's job is to define the blast radius, and it does precisely that: past results survive in completed runs, future runs stop scoring, and domain prompts are relabelled. This is exactly the context an agent needs before committing an irreversible-looking action.

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, action first and consequences second, with zero filler. Every clause conveys distinct information about the operation's effect.

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?

For a one-parameter destructive tool with a full safety annotation set and no output schema, the description covers the important unknowns (retention and downstream relabelling). It stops short of stating the return value or idempotency behavior for repeated calls.

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 100% for the single competitor_id UUID parameter, so the schema carries the definition and baseline 3 applies. The description adds nothing about the identifier, such as where to obtain a valid one or whether an unknown ID errors.

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?

"Stop tracking a competitor on its domain" is a specific verb plus resource and corrects the natural assumption that a delete destroys data. It does not contrast itself with update-competitor or add-competitor, so the agent must infer the boundary from names alone.

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?

The consequence clause implies when this is appropriate (permanently stop scoring a domain), but there is no explicit "use this when / use update-competitor instead when" routing and no preconditions such as needing the ID from list-competitors. Usage is inferable rather than stated.

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