desktop_match_image

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

The description discloses important behavioral traits beyond the readOnlyHint annotation: it states that scores are uncalibrated correlation, never semantic identity or click permission, that flat templates are refused, and that no new capture or input occurs. It also notes the optional system OpenCV requirement. The readOnlyHint annotation is consistent with the description's statement that no new capture or input occurs.

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 dense but well-organized, front-loading the core purpose before diving into parameter constraints and behavioral notes. Every sentence adds value, though the density of technical constraints could be slightly overwhelming. It is appropriately sized for the complexity of the tool.

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?

The description covers the essential context: prerequisites (retained and fresh IDs, same server and image scale), constraints (template_bounds ranges, threshold/limit ranges), behavioral caveats (uncalibrated scores, flat templates refused), and dependencies (optional OpenCV). While there is no output schema, the description adequately explains what results will look like in terms of non-overlapping candidates and distinct duplicates.

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?

Although schema description coverage is 0%, the description provides substantial parameter semantics: it explains that template_bounds requires x, y, width, and height in source returned-image pixels, with specific constraints on ranges. It also clarifies that results use target returned-image pixels and that threshold is finite 0–1 with limit 1–100. This compensates well for the lack of schema descriptions.

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 the tool's function: finding historical visual candidates from a selected screenshot crop in another retained screenshot. It uses specific verbs and resources (find, screenshot crop, retained screenshot) and distinguishes itself from siblings by focusing on historical matching rather than live observation or interaction.

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 explicitly states when to use this tool: when both IDs are retained and fresh, from the same server and image scale, and only the target must still have its captured layout. It also notes that historical source crops may come from a window that moved, providing clear context for when this tool is appropriate.

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