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

Annotations already declare non-read-only, non-destructive, closed-world behavior; the description adds real context beyond that: partial-update semantics ('Omitted fields remain unchanged'), idempotency requirement via request_id, API-key auth, and a $0.10 cost. It stops short of describing failure modes or invalid state transitions for a mutation tool.

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?

Five short, telegraphic sentences with zero filler, and the most decision-critical facts (ID source, patch semantics) come first. Every clause earns its place.

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?

The output schema exists, so return values need no prose, and safety is covered by annotations. But for a 19-parameter mutation with 11% schema coverage, the description leaves most of the update surface undefined, which is a meaningful gap for correct invocation.

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?

With 19 parameters and only 11% schema description coverage, the description carries the burden but documents just two fields: current_value (absolute, not delta) and request_id (required). The bulk of the surface — status transitions, target_type, habit_frequency, checkin_frequency, target_value constraints — is unexplained in both schema and description.

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 ('Patch one owned goal by goal_id') plus scope ('owned', single record), and names the sibling that supplies the ID ('from get_goals'). An agent can distinguish it from create_goal and get_goals without opening any 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?

Gives concrete usage rules: obtain the goal_id from get_goals, never guess an ID, and treat current_value as absolute rather than a delta. It does not explicitly route to sibling tools for creation or status-only changes, so it falls short of full when/when-not guidance.

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