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

Annotations already declare this as a non-read-only, destructive write. The description adds two useful behavioral details: batch operations cap at 25 items and results are verified per-ID. It does not mention the confirmation step needed to actually execute the write, nor any permission or account-scoping requirements beyond what the schema says.

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 tight sentences, front-loaded with the core action and scope, then mode details, then verification note. Every sentence carries information; no filler or redundancy.

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, multi-parameter write with no required top-level fields and no output schema, the description covers purpose, modes, and batch limit. It leaves out the two-step preview/confirm requirement that is critical for correct invocation (only hinted at in the confirm_id schema description), says nothing about profile_id, and gives only minimal output expectation ('esito verificato PER-ID').

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 only 50% schema description coverage, the description adds meaningful semantics: it resolves the ambiguity between single-mode (keyword_id + state) and batch-mode (items array) usage, states the ENABLED/PAUSED values, and imposes the max 25 batch limit. It does not explain profile_id, which lacks any description in the schema.

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: update the state (ENABLED/PAUSED) of one or more SP keywords. The single vs batch modes further clarify scope. It doesn't explicitly name a sibling tool it is not, but the combination of 'SP' and 'keyword' distinguishes it from the SB keyword, SP target, and bid-update siblings.

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?

Explains how to call it in single mode (keyword_id + state) and batch mode (items array, max 25), which is useful in-tool guidance. However, it gives no guidance on when to use this tool versus alternatives (e.g., ads_update_sp_keyword_bid) and omits any mention of the preview/confirm flow implied by the confirm_id parameter.

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