criar_treino

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

Annotations already declare a write operation (readOnlyHint=false, openWorldHint=true, destructiveHint=false), and the description reinforces this with the Garmin sync side effect and the user-approval gate, both consistent with openWorldHint. It says nothing about conflicts on an already-populated date, idempotency, or what happens on sync failure. With annotations carrying much of the load, this is adequate but thin.

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 purpose is front-loaded in the first sentence, then parameter notes are laid out one per line with no filler. Every sentence carries information the agent could not get from the schema, and the closing precondition is the right thing to end on.

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?

Covers the essentials for a 5-required-param write tool: purpose, external side effect, date bounds, payload syntax, and an approval gate. An output schema exists so return values need no explanation. Remaining gaps are the meaning of 'atleta' and 'nome' and conflict handling on repeat scheduling, so not fully complete.

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 0%, so the description must carry the burden, and it does for three of five params: date format AAAA-MM-DD with a 120-day forward range, valid sport values (Ride, Run, Swim, WeightTraining), and the Intervals.icu step syntax ('-' at line start). 'atleta' and 'nome' are left entirely unexplained — notably whether 'nome' is the workout title shown in the calendar — which keeps it from a 5.

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 ('Publica um treino planejado no calendário do atleta'), which reads clearly opposite to siblings like apagar_treino and atualizar_treino without needing to name them. The added detail that it syncs with Garmin sharpens what 'publish' means here. It stops short of explicitly routing against siblings, so not a 5.

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 precondition: 'Só chame depois que o usuário aprovar o treino', which is exactly the kind of gate an agent needs before a write. The date window (hoje até 120 dias à frente) further bounds legitimate calls. No explicit 'when not to use' or named alternative, so not a 5.

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