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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavior beyond the annotations: oversized documents hard-fail instead of silently truncating, and the tool performs no provider refresh or publishing. That is exactly the kind of consequence an agent needs, though a note on error shape/pagination is absent.

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, no filler, with the resource scope and lookup key front-loaded before the behavioral caveats. The second sentence packs two distinct constraints (oversize failure, no refresh/publish) into one clause, which is efficient but slightly dense.

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 read-by-id tool with an output schema (return shape need not be described) and full annotation coverage, the description supplies the missing pieces: identifier provenance and failure semantics. It is essentially complete, with only the id-format constraint left unaddressed.

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 0% and there is a single required `id` with no description in the schema, so the description must carry the meaning — and it does, specifying the value is a 'search identifier' (derived from a prior search, not an arbitrary key) and that its resolution yields source URL and provenance. A minor gap remains on length/format constraints.

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 (Read) and enumerates the exact resource types it resolves (brand, saved campaign, AI plan, cached Insights document) plus the lookup key. It's clearly distinct from list/search siblings, though it never explicitly names `search` as the tool that produces the identifier, so the sibling routing is only implied.

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?

Implies the precondition that the caller must already hold a 'search identifier', and gives two explicit exclusions: no provider refresh and no publishing. It never states when-not to use it in relation to a specific sibling (e.g. insightsRefresh or search), so it stops short of full when/when-not guidance.

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