cost_estimate

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Predict' combined with 'BEFORE dispatching' strongly implies a non-mutating, side-effect-free calculation, which is useful signal for an agent weighing safety. But it does not explicitly state that the tool does not dispatch or modify state, nor what inputs drive the estimate — whether it is a pure function of the three parameters or incorporates current conversation context.

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 11-word sentence that front-loads the verb and purpose. 'BEFORE dispatching' earns its place by adding workflow positioning that differentiates the tool from its siblings, and there is zero filler or 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 low-complexity tool with three scalar parameters, the description covers core purpose and timing — enough for an agent to decide WHEN to call it. But with no annotations and no output schema, the burden is higher: the 'token cost' framing versus per-million-token price inputs leaves the output ambiguous (estimated tokens, estimated dollars, or both), and the return value is never described.

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 description coverage is 0%, so the description must compensate, and it partly does: 'fan-out' maps to k_tasks and 'token cost' maps to the two price parameters. However, it never defines units (mtok = million tokens), states what k_tasks counts, or explains how the parameters combine to produce the estimate. The self-descriptive parameter names carry much of the remaining interpretive weight.

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 states a specific verb ('Predict') and resource ('token cost of an Algernon fan-out'), and the 'BEFORE dispatching' marker distinguishes it from operational siblings like dispatch_with_dependencies. An agent can tell this is a planning-stage estimation tool without opening the schema. The only minor weakness is reliance on the undefined domain term 'Algernon fan-out', but the core purpose is unambiguous.

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?

'BEFORE dispatching' gives explicit temporal context, telling the agent to run this during planning rather than execution, which clearly separates it from dispatch_with_dependencies and orchestrate_and_record. However, it names no alternatives and gives no when-not-to-use conditions or exclusions. Clear context, but the guidance stops short of explicit routing logic.

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