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

Annotations declare non-read-only, non-idempotent behavior but say nothing about what actually happens; the description fills that gap by disclosing that it returns a url, that the agent must open it in a browser, and that a follow-up call to wait_for_pick with the pickId is required. It does not cover failure modes (e.g., no matches) or how long the pick remains valid.

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?

Front-loads what the tool does and where the output goes, then the required follow-up step; no filler sentences. The final sentence is dense but every clause (returned url, per-OS open command, waitForPick handoff) carries actionable 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?

With no output schema, the description correctly explains the return value (a url plus pickId) and the end-to-end interaction protocol across two tools. It omits edge cases such as zero matches or user abandonment, which for a 7-parameter interactive tool is a modest but real gap.

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%, so the schema already documents q, goal, kind, count, stack, product, and screens. The description adds only loose hints ('a few matching references' for count, 'instead of searching' for screens) and no syntax or format detail, so the 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?

States a specific verb and resource ('show the user a few matching references side by side ... let them click the one to build from'), and explicitly contrasts itself with an alternative flow ('prefer this over sending full-page images'). An agent can distinguish it from get_screen_image and search_screens without opening a schema.

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?

Gives a clear selection condition ('whenever the user should decide') and names the alternative it should replace (full-page images). It does not spell out when not to use it versus search_screens or how to handle a no-match result, so it falls short of full when/when-not coverage.

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