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

The description adds real domain context beyond the annotations: what entities appear in the payload, how the result relates to the editor's picker and to cost-sync matching. It says nothing about mutation, auth scope, pagination, or result size, and the tool is declared readOnlyHint=false / idempotentHint=false despite being described as a pure read, so the agent gets no clarification on that tension. The added domain framing is useful but the behavioral profile for a listing call is left thin.

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 purpose is front-loaded in the first clause, and each sentence carries information. It is nonetheless dense and jargon-laden ('campaign_meta_links — the campaign editor's Facebook picker rows'), with em-dash parentheticals and product-specific references (Torvex) that slow comprehension on a first read.

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 no output schema, the description must convey the return value, and it does so in prose (link rows plus candidate tracker campaigns). It does not describe the shape of that payload (grouped per Facebook id vs. flat lists), pagination, or what happens when `ids` is omitted despite both parameters being optional. Adequate orientation, incomplete for an agent that must consume the output.

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%, so baseline is 3, but the description goes further by explaining that `q` narrows the candidate tracker campaigns by name or alias, distinct from `ids` which selects the Facebook side. That framing clarifies the two-part result set in a way the schema's one-line field descriptions do not. It still omits behavior for empty `ids` (does it return all links or only candidates?).

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 description states concretely what is returned: the campaign_meta_links rows that map given Facebook campaign ids to tracker campaigns, plus the manual/meta tracker campaigns a link can point at. That is a specific resource with a clear read verb ('what ... are linked to'), and the mention of the Facebook picker and the extension overlay separates it from write-side siblings like link_meta_campaign and unlink_meta_campaign. It never names those siblings explicitly, which keeps it short of a 5.

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 strong situational context ('what the Torvex browser extension shows on every Ads Manager campaign row') and a diagnostic cue ('an unmatched FB campaign in the cost sync is exactly a missing link'), which implies when to reach for it. However, it never states when NOT to use it or which sibling to prefer for adjacent jobs (list_campaigns, get_meta_overlay, link_meta_campaign), so the guidance is implied rather than explicit.

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