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

Annotations declare destructiveHint=true and idempotentHint=false, and the description goes well beyond that: it explains that omission preserves, null clears, null/[] clears references, that status-only updates preserve description/due date/references, that title and status cannot be null, that the complete saved action is returned, and it rules out original-author restrictions, board transition, external publication and Scan launch. That is unusually rich disclosure of mutation semantics and authorization for a tool flagged destructive.

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 single most important rule (at least one editable field) and kept short, with every sentence carrying a rule. The middle clauses are densely comma-packed, and phrases like "board transition" are cryptic without domain context.

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?

An output schema exists and the description notes it returns the complete saved action, so return-value detail is not required here. Combined with the partial-update rules, permission note and side-effect exclusions, it is nearly complete; only error/validation behavior for bad IDs is unaddressed.

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 75%, and the description adds meaning the schema does not: the null-clears vs omission-preserves rule for every editable field, the non-nullable constraint on title and status, and trim/dedup behavior for references. It stops short of documenting status enum semantics or error behavior for invalid IDs.

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 with scope: "Update one saved action." The singular "one" plus the parameter list makes the operation unambiguous. It does not, however, differentiate itself from its close siblings such as update_recommendation_note or create/delete_recommendation_action, so the agent must infer routing from the 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?

The description gives operative invocation rules ("Supply at least one editable field") and field-level preserve/clear behavior, but it never says when to choose this tool over update_recommendation_note, create_recommendation_action, or delete_recommendation_action. Usage is implied rather than scoped against alternatives.

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