crosspad_screenshot

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

Discloses the two distinct behavioral modes, save-to-disk vs return-inline, and transparently quantifies the token cost tradeoff of '~50-150k tokens'. It also documents the save location (<crosspad-pc>/screenshots/) and that filename is ignored when return_inline=true. Exceeds what annotations (readOnlyHint=false, destructiveHint=false) convey, adding meaningful price/behavior context beyond schema.

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?

Two sentences, zero waste, front-loaded with the core purpose. Every clause earns its place — the token-cost warning is the most decision-relevant detail and is placed exactly where it matters.

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?

Has an output schema (so return docs aren't the description's job), full param coverage, and the description fully addresses the mode decision that matters most. Both the cheap default and the expensive explicit option are covered, making this complete for an agent deciding whether/how to invoke it.

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 100% and both parameters are well described in the schema itself. The description reinforces the return_inline tradeoff and the filename save path, but adds marginal value beyond what the schema already documents — mainly the token-cost framing which is genuinely useful.

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?

Clear verb+resource: 'Capture a PNG screenshot from the running PC simulator'. Distinct from siblings like crosspad_log or crosspad_input — nothing else captures a screen. The context marker '[PC sim]' scopes it appropriately.

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?

Explicitly distinguishes between two modes with clear when-to-use guidance: default return_inline=false is 'cheap, no token cost', while return_inline=true is explicitly reserved 'ONLY when the LLM needs to actually see the image' and warns of the token burn (~50-150k). Alternative usage contexts are well articulated.

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