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

The annotations already provide idempotentHint=true, but the description adds important nuance beyond that: a repeated call 'repositions it instead of creating a duplicate,' and numeric lean/rationale is refused. It also explains why numbers are rejected (investment-advice concern), which is genuinely useful behavioral context not visible in the schema or 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?

The description is two sentences with no filler. The action is front-loaded, and the second sentence packs the two highest-value constraints (idempotent repositioning and qualitative-only input) without redundancy.

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 11 parameters, the description gives an agent the essential operating knowledge: what the tool does, when retries are safe, and what input will be rejected. It falls slightly short of a 5 because it does not describe the return behavior or clarify several optional metadata params, though none are required for a correct basic invocation.

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 schema description coverage at only 36%, the description compensates for the most important parameter ambiguity: lean and rationale must be qualitative, and it explains the reasoning behind that constraint. It also frames the required event, lean, and rationale fields in one sentence. Optional metadata fields like tags, category, and URLs are still left to their names, but they are largely self-evident and optional.

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 uses a specific verb and resource: 'Record a new call on your book,' with concrete scope ('the event, which way you lean, and why'). It also clarifies the unusual semantic that opening an already-held call repositions it rather than duplicating it, which distinguishes this from the sibling fm_reposition and fm_close_position tools.

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?

It gives clear context by explaining the idempotent behavior and telling agents they may 'safely re-run its loop,' which is directly actionable for retries. However, it does not explicitly name fm_reposition or fm_close_position as alternatives for repositioning or closing scenarios, so exclusions are only implied.

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