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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world access, so the safety profile is covered; the description adds genuinely new context with "any member of the business can read," which is an authorization fact not in the annotations. It does not cover pagination or result-size limits for the "recent campaigns" list, and "Read-only" partly repeats readOnlyHint.

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?

Front-loaded with the core read semantics, then the parameter branching, then the permission note — a sensible order with no filler sentences. The middle clause is a long, heavily nested list of returned fields, which costs some scannability but every element carries information.

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 read-only, three-parameter tool with an output schema already documenting return values, the description covers what is read, how parameters change the shape of the response, and who may call it. The only meaningful omission is any hint about how many "recent campaigns" are returned or whether results are ordered/limited, plus the unexplained required business_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?

Schema coverage is 67%, and the description usefully disambiguates the two optional parameters by explaining that sender_id switches the response to that domain's DNS records rather than the campaign view — meaning beyond the schema's terse "Optional" notes. However, business_id is required yet never explained in either the schema or the description, leaving a real gap; baseline 3 is appropriate given the schema does much of the work.

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?

Opens with a specific verb+resource ("Read a business's email campaigns") and then enumerates the three concrete views returned: sending addresses and setup readiness, recent campaigns with status/fingerprint/outcome counts, and emailable customers. This is clearly distinguishable from the write-oriented siblings (launch/cancel/draft) and from consent tools, which is exactly the differentiation a reader needs.

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?

Gives explicit mode-selection guidance tied to parameters: "Pass campaign_id for one campaign, or sender_id for the DNS records that sending address's domain needs," which tells the agent how to branch between the three payloads. It stops short of naming a sibling alternative (e.g. check_email_sender for standalone sender checks) or stating exclusions, so it falls just below the top band.

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