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

Goes well beyond the annotations, which only say non-read-only, non-destructive, non-idempotent. The description discloses the human approval loop (shown on the phone for save or drop), the auto-save bypass, that the previous version is retained, and a size ceiling of about 30,000 characters.

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: purpose, exact call sequence, then side effects. The workflow and the version requirement are front-loaded, and even the trailing character limit is operationally necessary.

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 non-destructive mutation with a review step, the description covers prerequisites, side effects, version retention and size limits. With no output schema, it never says what the call returns (a pending proposal, a confirmation), which is the one thing an agent cannot infer.

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 schema already documents all three parameters. The description still adds value by explaining provenance: `version` must be the value get_routine returned and `written` must be the whole routine with `from` preserved, which is the semantics that matters for correctness.

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 and resource ('Suggests a change to one of the person's routines') and, via 'one of the person's routines', implicitly separates it from propose_new_routine. It never names the sibling explicitly, so an agent must infer the boundary from the tool names rather than the prose.

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?

Gives an explicit prerequisite workflow: fetch with get_routine, edit the `written` form, send the whole thing back with the returned version. It does not state a when-not case (e.g. use propose_new_routine instead when the routine does not yet exist), which is the only gap.

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