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

Annotations declare destructiveHint=true and idempotentHint=true, and the description earns credit beyond them by naming what is destroyed ("a definition replaces the saved one entirely"), clarifying merge-vs-replace semantics (omitted fields are kept), and explaining how to clear a field with null/empty string. It also discloses that the change is persisted immediately and that reason is surfaced on an approval card, which is material context an agent otherwise would not have.

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 action, then partial-update rules, then the ordered workflow, then prerequisites. Slight redundancy with the schema text on the description field and a trailing skill-loading instruction that could be a preamble, but no sentence is filler.

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 tool whose definition argument is a deeply nested AST, the description correctly delegates the structure to the cohorts skill and points at list_cohorts/run_cohort_definition for building and validating it. It never states what the call returns on success, a minor gap given there is no output schema, but the caller's decision-relevant information 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 schema already documents name, reason, cohortId, projectId, definition, description, and environment, including the omit-to-keep behavior. The description reinforces the partial-update semantics and the "start from list_cohorts' definition" rule, but it adds little about parameters that the schema descriptions do not already state, 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?

"Change a saved cohort's name, description, and/or definition" gives a specific verb plus resource and enumerates the mutable surface, which cleanly separates it from create_cohort, delete_cohort, and list_cohorts without needing the schema opened.

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 supplies an explicit workflow: load the manage-cohorts/cohorts skills first, start from list_cohorts' definition, and dry-run with run_cohort_definition before saving. What it does not do is state the inverse condition (e.g. "use create_cohort for a brand-new cohort"), so the alternative-selection guidance is strong but not complete.

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