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

Annotations already declare readOnlyHint=false and openWorldHint=true; the description adds that credentials never leave the server and that mutations must be previewed then confirmed with a token, which is genuine safety context. It still omits what a mutation actually affects, whether deletes are possible, and any rate/limit behavior — and the wording reads as generic boilerplate shared across sibling proxies.

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, front-loaded and free of filler. The opening sentence is wasted duplication of the title, but everything else earns its place.

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?

This is a complex open-world proxy with 11 parameters, multiple HTTP methods, three pagination schemes and no output schema — yet the description never explains what an SD target clause is, what list versus create/modify body shapes look like, or what the response contains. For a tool of this complexity the description is markedly under-specified.

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 every one of the 11 parameters (method, body, queryString, fetchAll, confirmationToken, etc.) is documented in structured fields and the description need not repeat them. The description's only parameter-adjacent value is the preview/confirmation note, which aligns with confirmationToken but adds nothing beyond the schema; baseline 3 applies.

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, 'Amazon Ads: sd/targets API,' simply restates the title and the name's own token 'sd_targets' — it never explains in plain terms that this is the Sponsored Display targeting-clause endpoint supporting list/create/modify. It also gives no cue to distinguish it from siblings such as nexscope_data_amazon_ads_developer_proxy_sd_targets_extended or sd_negative_targets.

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?

'Mutations require preview and confirmation' implies a two-step workflow for writes, which is a useful procedural hint. But there is no guidance on when to pick this tool over the *_extended counterpart, sp_targets or sb_targets, and no stated preconditions beyond needing a connection.

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