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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description still adds non-obvious behavioral facts: the link is shared across Sonar accounts and unlinking affects other accounts tracking that competitor, plus plan eligibility (Indie/Agency, trial counts) and the required write scope. These are exactly the consequences an agent cannot infer from structured fields.

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 short sentences, no filler: mode first, action second, constraint third, side effect and prerequisites last. Every clause carries information an agent needs (write mode, target, exclusivity, blast radius, plan/auth).

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 simple three-parameter mutation with no output schema, the description covers purpose, exclusivity, side effects and prerequisites. It does not say what happens on a no-op (link not present, only implied by idempotentHint) or what the call returns, which would complete the picture for an agent handling errors.

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 description coverage is 100%, so the schema already documents all three parameters and their formats. The one thing the description adds — that advertiser_id and account_id are mutually exclusive ('Pass exactly one') — is genuinely valuable because the schema itself does not express a oneOf constraint, but that is the only added semantic, so the baseline-3 level fits.

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 first sentence names a specific verb (remove/unlink) and a specific resource (competitor → Facebook page advertiser_id or TikTok account link), and the title plus the 'WRITE tool' prefix make the direction of the operation unambiguous. It is clearly the inverse of the sibling sonar_ad_spy_link, so an agent can select it 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 states the triggering condition clearly ('remove a wrong ... link') and gives the hard operational rule 'Pass exactly one', which is the main way to misuse this tool. It stops short of explicitly naming sonar_ad_spy_link as the tool to use for creating a link, so the routing guidance is implied rather than spelled out.

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