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

Annotations declare destructive, idempotent and non-read-only, and the description substantiates them: items left out are deleted, updated_at changes, optimistic concurrency via expected_updated_at, and role-based authorization errors. It also discloses the return value (the plan and its total hours), adding context beyond the hints.

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-loads the replace semantics and the sibling differentiation, then layers constraints, error codes and return value in short declarative sentences. Dense but every clause carries operational information with no 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?

Even without an output schema, it states what is returned, what is destroyed, what errors arise, and what authorization is needed. For a destructive whole-collection replace with four required params, this covers everything an agent needs to call it safely.

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 0%, so the description carries the load. It explains the items array well, including the keep/new/delete semantics of a nested id, but experiment_id and idempotency_key are never discussed and expected_updated_at is only implied through the STALE_EXPERIMENT concurrency note.

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 ('Replace the whole action plan of an experiment') plus the concrete payload (task list with title, estimated_hours, assignee_id, completed). It also explicitly separates itself from hypotize_experiment_update, which it says does not touch the action plan.

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 the full replace contract: which items to keep (id present), add (id absent), and remove (omitted entirely). It also names preconditions (assignees must be project members; editor/owner role required) and the failure modes (STALE_EXPERIMENT, INSUFFICIENT_ROLE with required_roles).

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