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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this mutates saved state. The description adds no further behavioral context such as whether the action is reversible, whether re-saving restores it, or what happens to progress data attached to the session. In a wellness domain the crisis/medical carve-outs add some useful scope framing, but nothing about the mutation itself.

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 with the primary trigger front-loaded. The two 'Not for...' sentences are somewhat repetitive and domain-oriented rather than selection-oriented, but they are short and not padded.

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 two-parameter destructive tool with no output schema, the annotations carry the safety profile and the schema carries the parameters, so the remaining gap is guidance on alternatives (save_session) and reversibility. The description covers the trigger condition adequately but leaves the agent to infer the inverse operation.

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 description coverage is 100%, and the schema already explains both session_id (from find_sessions or play_session) and the tap token from keep_progress. The description adds no parameter meaning beyond that, 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?

The description states a concrete action on a concrete resource: taking a session off the user's saved list, which pairs unambiguously with the tool name unsave_session. It does not explicitly name the inverse sibling save_session, so the distinction is implied by name rather than stated.

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 when-to-use condition ('when the user wants a session taken off their saved list') plus three when-not conditions. The exclusions are domain guardrails (medical, emergency, crisis, general chat) rather than tool-selection alternatives, so it clarifies conversational scope but not which sibling to pick instead.

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