fl_set_precount

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

Annotations already declare destructiveHint and non-idempotence, so the description adds value by revealing that the tool will later 'verify' the set value on a future FL tick, implying a follow-up check rather than a fire-and-forget write. This is useful behavioral insight beyond the schema. No contradiction with annotations.

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?

A single two-clause sentence perfectly communicates the core action and the verification behavior without any filler or unnecessary prose. It is front-loaded with 'Set...' and the rest is unnecessary but valuable information.

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 the main action and verification but does not mention important preconditions or effects that are not already in the schema, such as failure behavior when session_fingerprint mismatches or what happens to existing precount. The output schema likely covers return values, so this is adequate but not exhaustive for a mutation tool.

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?

The schema already provides 100% coverage, each parameter having a clear description (e.g., 'Absolute countdown-before-recording state'). The description's 'absolutely' is redundant with the schema's 'Absolute'. No additional semantic meaning is given, so a baseline 3 is appropriate.

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 description 'Set recording precount absolutely and verify it on a later FL transition' clearly identifies the specific verb (set), resource (recording precount), and the absolute (non-toggling) nature, plus a verification side-effect. This distinguishes it from siblings like fl_set_recording, which controls recording state, without confusion.

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 no explicit guidance on when to use this tool versus others, such as fl_set_recording or fl_set_metronome. It doesn't mention prerequisites, exclusions, or alternatives, leaving the agent to infer the appropriate call from the tool name alone.

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