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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description only needs added context — and it supplies it: results are drill cards from a 48-drill library containing steps, a cue and reps. It does not say how results are ranked or what happens when nothing matches, which are the remaining behavioral gaps.

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 trigger condition, then coverage vocabulary, examples, exclusions, and only then the return note — a sensible ordering. The long comma-separated fault list and the closing 'Skills:' dump are dense but earn their place as matching vocabulary for retrieval; a little trimming would still help.

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 5-parameter search tool with no output schema, the description covers intent, exclusions, return shape and vocabulary. Missing only how limit/max_minutes shape the response and whether results are ranked — minor against how much is already specified.

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 60% and the description compensates well where it matters: it tells the agent to pass the golfer's own words as query, and the trailing Skills list effectively enumerates valid skill values beyond the schema's single example. limit and max_minutes remain undocumented in both places, though their bounds make them largely self-evident.

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 ('find golf drills') and immediately scopes it to the golfer-intent case. It distinguishes itself from siblings by naming diagnose_ball_flight as the path for unnamed ball-flight problems and excluding non-drill domains like tee times, prices and rules.

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?

Explicit when-to-use is given via trigger phrases ('how do I fix my slice', 'I come over the top'), plus a concrete when-not case routed to diagnose_ball_flight and a negative list (tee times, course info, equipment prices, distances, rules). Alternatives are named, not merely implied.

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