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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description reveals that setting featured=true automatically un-features other active goals, that the server rejects featured on frequency goals, that unknown exercise_ids are rejected, that coach-proposed goals start with ratified=false, and that goals are never deleted but superseded. This is rich behavioral context the annotations alone cannot provide.

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?

The description is long but proportionately so for a tool with a deeply nested goal object and multiple workflow rules. It is front-loaded with the core operation, then systematically covers each goal type, validation constraints, featured behavior, and lifecycle transitions. Each paragraph earns its place with non-redundant, actionable guidance.

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 description covers nearly every meaningful field and behavior, and the output schema exempts it from explaining return values. However, the required 'kind' enum (outcome/process/performance) is never explained and has no schema description (coverage 0%). While goal_type is thoroughly handled, the distinct concept of 'kind' remains underdocumented, leaving a gap for agents that must populate this required field correctly.

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 schema description coverage at 0%, the description fully compensates by explaining the semantic meaning of goal_type values (milestone, weekly_volume, trend, maintenance, plain process), their required nested fields (e.g., muscle+band for weekly_volume, baseline_value+tolerance_pct for maintenance), and the roles of id, featured, status, ratified, review_date, and supersedes_goal_id. The raw schema only lists enums and null types, so the description adds decisive value.

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?

The opening sentence 'Create or update a training goal (pass `id` to update)' names a specific verb, resource, and the key update selector. It also enumerates all goal_type variants and their field requirements, making the tool's purpose unmistakable and clearly distinct from sibling tools like upsert_exercise and get_goals.

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 explicit operational guidance: when to update (`pass id`), when to check list_exercises and use upsert_exercise for new exercises, when to avoid featured (frequency goals), and the required two-call workflow for achieved milestones. It also states the hard rule 'Never delete goals — supersede with status=revised/abandoned/achieved', leaving no ambiguity about appropriate use.

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