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

Annotations already declare non-readOnly, non-destructive, idempotent and closed-world, so the description's restatement of idempotency earns little on its own — but it adds the real granularity key "per (campaign, FB id)". It also discloses downstream effects beyond the annotations: the cost sync books spend from the next run, and the Ads Manager overlay and status mirror pick the link up immediately. Missing: error behavior when the FB campaign is already linked to a different tracker campaign.

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 is front-loaded in the first clause, and the effect/idempotency details follow as supporting context. It is dense but every clause carries information; only the idempotency restatement partially duplicates the annotation.

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 mutating tool with a nested object, 5 parameters and no output schema, the description covers side effects and idempotency well but leaves ad_account_id and fb_campaign_name unexplained and says nothing about failure or re-link cases. Adequate, but there are clear gaps an agent would hit.

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?

With 40% schema coverage, the description fills some gaps: campaign_id is an existing tracker campaign of manual or meta type, and fb_user denotes the logged-in FB user's tokenless profile. It says nothing about ad_account_id or fb_campaign_name (the name snapshot kept on the link), so a meaningful portion of the 5-param surface, including the nested object, remains undocumented.

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 both resources: "Link one Facebook campaign to an existing tracker campaign (manual or meta type)". The naming contrast with unlink_meta_campaign and create_campaign_from_meta makes the distinction obvious without opening another 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?

Prerequisites are implied well: the tracker campaign must already exist and be of manual or meta type, and the caller must act under the logged-in FB user's tokenless profile. However, there is no explicit when-to-use vs. when-not guidance and no alternative sibling is named (e.g. create_campaign_from_meta for the not-yet-existing case).

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