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

readOnlyHint=true already establishes the safety profile, and the description adds meaningful extra context: the shape of each returned programme (structure, suitability, progression rule, cautions) and the constraint that each day carries a modality rather than sets/reps. It does not mention result limits or pagination behaviour beyond what the schema's 'limit' implies.

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?

Dense and largely front-loaded, with each sentence carrying distinct information (contents, sequencing, search modes, downstream constraint). The 14-item programme enumeration in the parenthetical is long, though it does double as search vocabulary, so it mostly 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?

With no output schema, the description carries the burden of describing returns, and it does so adequately (structure, suitability, progression, cautions). Combined with the sequencing rule and search modes, an agent has enough to call it correctly and use the result; only the relationship to the user-template siblings is left implicit.

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 60% schema coverage, the schema documents goal, query and experience but leaves daysPerWeek bare. The description compensates by showing query examples ('hyrox', 'ppl', 'couch to 5k') and by grouping goal + daysPerWeek + experience as a combined filter axis, which clarifies daysPerWeek's role — meaningful added meaning beyond the schema.

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 names a specific resource (named training programme templates) and enumerates concrete contents — day-by-day structure, suitability, progression rule, cautions — so an agent knows exactly what comes back. It relates itself to create_workout_plan, but does not contrast itself with the confusable siblings get_workout_plan_template and list_workout_plan_templates, leaving a small differentiation gap.

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 sequencing ('Call this BEFORE create_workout_plan') plus two concrete search modes ('search by name' or 'by goal + daysPerWeek + experience') give real when-to-use guidance. It even prescribes downstream behaviour ('build those sessions with matching modality ... never sets/reps for a run'). There is no when-not-to-use statement or contrast with the template-listing siblings, so it falls short of a 5.

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