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

Annotations declare readOnlyHint=false, so this is a state-changing call, yet the description never says what changes (starting a session, consuming the tap token, recording progress). It does add real behavioral context beyond the annotations in the form of the 7-calm-nights eligibility prerequisite, which earns credit, but the mutation semantics remain undisclosed.

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 with the usage trigger and followed by the exclusions. No filler, though the opening clause is slightly tangled and could state the action more directly.

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 three optional params fully documented and no output schema, the main remaining gap is what the caller gets back and what the call does to user state. For a non-read-only tool, that omission matters more than the eligibility detail that is present.

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 the tap token, local date and BCP-47 language are already fully documented in the schema. The description adds no parameter guidance of its own, so 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 description frames this as delivering "tonight's session" and continuing "their sleep plan," but never states a concrete verb or what the tool actually returns (audio, a session id, a progress record). The opaque name "tonight" is only partly rescued by the phrase "tonight's session," leaving the agent to guess the operation.

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?

It gives an explicit trigger ("user has started 7 calm nights and asks for tonight's session, or to continue their sleep plan") plus explicit exclusions ("Not for medical questions, emergencies or a crisis. Not for general chat about meditation."). It stops short of naming which sibling handles the excluded cases, but the when/when-not framing is clear.

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