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 real value by enumerating what the response contains: per-CDP integration counts, sends/reads direction grouping, which CDPs list it or not, deployment mode, doc links and the cdphub page. It omits the failure case (unknown tool name) and whether records are cached or refreshed.

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 action, and the long enumerative clause is all substance about returned fields rather than filler. It is a single run-on sentence though, and the return-content list could be split or trimmed for scanability.

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 one required parameter, full schema coverage, complete annotations and no output schema, an agent has everything needed: what to pass, what comes back, and how the data is grouped. The description carries the return-shape burden that the absent output schema would otherwise leave undefined.

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?

Only one parameter and schema coverage is 100%, with the schema already documenting 'name' and giving examples. The description's examples ('Snowflake, Braze, Google Ads or The Trade Desk') reinforce what counts as a valid name, but add little 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?

States a specific verb ('look up') and a specific resource ('one marketing or data tool in CdpHub's directory'), with concrete examples. It is clearly separable from get_cdp (a CDP, not a tool) and list_cdps/search_directory, which operate on sets rather than a single named entity.

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?

'Use it for any question about one tool' gives a clear selection rule, and the emphasis on a single named tool implicitly rules out the list/search siblings. It never explicitly names get_cdp or search_directory as the alternative when the target is a CDP or a fuzzy query, so the routing is inferable rather than stated.

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