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

Annotations only declare readOnlyHint=false/openWorldHint=false/destructiveHint=false, which is a thin safety profile. The description adds genuinely new behavioral context: the write is immediately persisted and visible ('will immediately appear in the user's Mobela app') and that IDs must come from another tool. Permissions and failure behavior are still unstated.

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?

Three short sentences, action first, prerequisite second, side effect third. No filler, no repetition of schema content.

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 mutation tool with a rich 100%-covered schema and no output schema, the description covers purpose, prerequisite, and the key side effect. It notably omits what the call returns (e.g. the new template's ID), which an agent may want for follow-up calls.

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 100%, so the baseline is 3 and the schema carries field-level detail. The description still adds meaning beyond the schema by establishing the provenance/validity constraint for the required exercises IDs ('valid exercise IDs' from get_exercise_library).

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 ('Create and save a new routine') plus the destination surface ('the user's Routines tab'), which no sibling offers since all siblings are get_* readers. An agent can immediately tell this is the single creation path for routines.

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 an explicit prerequisite and ordering rule: 'Always call get_exercise_library first to get valid exercise IDs.' It does not name when NOT to use it (e.g. use get_my_templates to view existing routines), so it stops short of full alternative coverage.

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