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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds what annotations cannot: the referential-integrity consequence (queries and cohorts referencing it keep a broken reference), the server-side guard for active/upcoming experiments, and the required workflow prerequisite (load_skill). That is substantive behavior beyond structured fields.

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 and permanence, then hazards, then workflow. Five short sentences all earn their place, though the reason/confirmation instruction is slightly split across two sentences and could be tighter.

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 destructive 4-param tool with no output schema, the description covers the irreversible effect, the blocking conditions, the side effects on referencing objects, and the required pre-call workflow. Nothing an agent needs before invoking it is missing.

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% and each parameter is already documented (reason is 'why you are making this change', cohortId from list_cohorts, etc.). The description only reinforces 'explain it in reason' and gives the cohort-name confirmation requirement; it adds little syntax or format meaning beyond the schema, 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?

Specific verb 'Permanently delete' plus resource 'saved cohort' plus scope 'current project'. It is clearly distinguished from update_cohort and create_cohort, and the permanence qualifier separates it from reversible operations.

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 explicit when-to-use preconditions (confirm exact cohort by name with the user first, load manage-cohorts skill first) and an explicit when-not condition (refused while an active or upcoming experiment targets it), plus the alternative for finding the cohort (from list_cohorts in schema).

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