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

Annotations already cover the safety profile (mutation, idempotent, non-destructive), and the description adds real value beyond them: partial-update semantics ('Null leaves a field as it is') and the fact that the call returns an Undo. It stops short of explaining what the Undo covers or what happens if the session was already in the requested status.

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 trigger, then field semantics, then the exclusion — no filler sentences. The phrase 'notes and gym as they say' is a little loose compared to the precision elsewhere.

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 6-parameter mutation with sparse schema descriptions but a present output schema, the definition covers activation, field meaning, null behavior, and routing to the right sibling. Return-shape detail is rightly delegated to the output schema.

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 only 17%, so the description carries the burden: it decodes the status enum values (IN_PROGRESS starts, DONE finishes, SKIPPED skips), gives a range for feeling (1 to 5), and explains that null is a no-op for any field. It does not clarify why the schema types feeling as a string, nor restate sessionId, but the essential semantics are covered.

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 pairs specific verbs (starts, finishes, skips) with the resource (the session) and enumerates the updatable fields (status, feeling, notes, gym). It also names the sibling it is not (move_session), so an agent can distinguish it without opening either schema.

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 ('when the person starts, finishes or skips the session, or says how it felt') and an explicit exclusion with the correct alternative ('Do not use to move a session to another day; use move_session'). Nothing about routing is left to inference.

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