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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description then adds value with the default sort direction, the returned payload shape { meta: { next }, calls }, and the fact that recording URLs are included by default and in-progress calls are excluded. It omits any note on rate limits or whether includeActive changes result volume, which keeps it below a 5.

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: what it lists, how to control ordering and filtering, and what comes back. The default-ordering caveat is front-loaded because it is the most likely source of agent error.

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 nine-parameter read tool with no output schema, the description supplies the return envelope and the key defaults, and the schema covers the rest. It is slightly thin on pagination flow (next/limit interplay) but an agent has enough to call it correctly.

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 100% schema description coverage, the schema already documents every parameter including the sortOrder enum semantics and cursor usage. The description mostly restates the schema's ordering and filtering facts rather than adding format or edge-case detail, so the 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?

It states a specific verb and resource ("List call records") and enumerates the returned fields (caller, direction, duration, assigned user/team, recording URLs), which clearly separates it from spokephone_get_call. However, it never names a sibling tool or says explicitly that single-call retrieval belongs to get_call.

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?

"pass sortOrder descending for the latest calls" and "Filter by time window or the external party's number" give concrete usage context for the two main axes (ordering and filtering). No when-not guidance or alternative tool routing is offered, but the usage context is clear.

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