integrate

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

Annotations already indicate non-read-only and non-destructive, and the description adds significant behavioral context: it states 'ALWAYS async' (a critical execution trait), the refusal condition for fewer than 3 frames, and that it reports rejected-pixel percentage (useful for diagnosing input quality). These go beyond the sparse annotations, though it doesn't describe all side effects or output details.

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 a dense single sentence packed with information, avoiding fluff. It front-loads the primary purpose and then cascades through algorithmic rules. While it's structured as a run-on, it is still efficient and every clause contributes meaning. It could benefit from bullet points, but for the information density it remains concise.

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?

Given the tool's complexity (14 parameters, no output schema, sparse annotations), the description covers the core algorithmic decisions and key constraints but leaves many parameters unexplained (e.g., sigma_low, sigma_high, lnorm_files, drizzle_files, large_scale_clip_high). An agent may struggle with advanced configurations, but the description is sufficient for standard integration tasks with defaults.

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 by explaining key parameters: rejection algorithm based on frame count, normalization behavior (additive+scaling or LocalNormalization), and weight source (SSWEIGHT or PSF). It also explains the 'force' param via the refusal condition. However, it doesn't cover many other parameters like sigma_low, drizzle_files, or keep_open, so it's not complete but does add substantial value for critical parameters.

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 clearly states 'ImageIntegration of registered frames → master light .xisf', identifying the verb (integrate), resource (registered frames), and output (master light). It is specific and unambiguous, but it does not explicitly differentiate from siblings like fast_integrate or drizzle_integrate, so it earns a 4 rather than 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?

The description provides operational constraints ('Refuses < 3 frames without force', 'ALWAYS async') but offers no guidance on when to choose this tool over alternatives such as fast_integrate or drizzle_integrate. There is no mention of when-not or preferred alternatives, leaving selection entirely to the agent's inference.

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