Search Visual Memory

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

Annotations already indicate the tool is read-only, idempotent, and non-destructive, so the description does not need to restate these. However, it adds minimal behavioral context beyond purpose—no mention of result ordering, pagination, or how the 'fast'/'semantic'/'thorough' strategies affect behavior. The description is accurate but does not enrich the annotation-provided safety profile.

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 single, tightly worded sentence that immediately conveys the tool's purpose and primary input methods. There is no redundancy or filler; it earns its place by being clear and succinct.

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 moderate complexity (8 optional parameters, no output schema), the description is functional but thin. It does not explain what a 'visual state memory' is, what the return payload looks like, or how to choose among strategies. The annotations and schema cover safety and parameter details, but the description leaves gaps around expected output and usage nuances.

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?

The input schema has 100% description coverage for all 8 parameters, so the baseline is 3. The description mentions three of the search modalities (screenshot, text query, accessibility tree), but does not add semantics beyond what the schema already provides for parameters like 'limit' or 'response_format'. It does not clarify how 'strategy' selection impacts results.

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: searching visual state memory using three distinct input modalities (screenshot image, text query, accessibility tree). This specific verb+resource combination distinguishes it from sibling tools like 'analyze_screenshot' or 'list_visual_specs'.

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 implies when to use the tool (when you need to search visual memory) but provides no explicit guidance on when not to use it or which sibling tool might be a better alternative. For instance, it doesn't mention that 'list_visual_specs' could be used for listing specs or that 'compare_states' might be better for comparing states.

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