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

Annotations only flag destructive/idempotent; the description adds the substantive behavioral context: recorded positions survive the removal, sibling extensions and shared store listings are untouched, partitioning is per store language, and an account sign-in is required with example commands. This is exactly the extra context annotations cannot convey.

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 core action and the 'positions kept' caveat are front-loaded, with scope, isolation, and locale semantics following in descending importance. It runs slightly long across five short paragraphs, but no sentence is 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?

For a destructive mutation with no output schema, the description covers the important ground: what is destroyed versus preserved, cross-tenant isolation, locale identity, and auth prerequisites. It doesn't state error behavior for an untracked term, a minor remaining gap.

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%, and the schema already explains locale canonicalisation and the extension_id source, so the baseline is 3. The description reinforces the locale parameter's meaning ('a term is tracked per store language' with en/de independence) but adds no syntax beyond what the schema states.

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 ('Stop tracking a search term for an extension') and immediately bounds the scope ('across every store it was tracked in'). The clause 'Positions already recorded are kept; only the tracking stops' distinguishes it cleanly from a delete-history operation, so an agent can separate it from add_keyword or remove_competitor without opening the schema.

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 concrete alternative for the related question ('Call list_keywords for the languages an extension already tracks') and clarifies the blast radius ('Other extensions tracking the same term are unaffected'). What is missing is an explicit when-not-to-use or a statement of what happens when the term isn't currently tracked.

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