Advanced Device Search

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds significant context beyond these: explains the query structure (AND/OR groups), warns about API key scope issues, and details the interpretation of outstanding_patch_severity field (string 'none' vs null/absent). No contradictions with annotations.

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 appropriately sized, front-loaded with the core purpose, and each sentence serves a purpose. It follows a logical flow: purpose, example, query structure, warnings, field interpretation. No unnecessary repetition or filler.

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 (structured query language, 4 parameters, no output schema), the description covers the query structure, key caveats (API key scope, field behavior), and references helper tools. It lacks explicit pagination details (e.g., how page works) and does not enumerate possible output_format values. However, the provided information is sufficiently complete for the intended advanced use case.

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 description coverage is 0%, so the description must compensate. It provides extensive semantic meaning for the key parameter 'query', including the dict structure, examples for device and tag searches, and pointers to helper tools. 'limit' is mentioned as page size. However, 'page' and 'output_format' receive minimal explanation. Overall, it adds substantial value for the most complex parameter.

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 defines the tool as executing an advanced device search using a structured query language, with explicit examples of complex queries (e.g., 'find all Windows devices not seen in 30 days'). It distinguishes from sibling tools like list_devices and search_devices by emphasizing the advanced querying capability and referencing related helper tools (get_searchable_fields, device_search_typeahead).

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?

Provides explicit guidance on when to use this tool (for advanced, complex queries) and when to use alternatives (simpler searches via list_devices or search_devices). It instructs users to leverage get_searchable_fields and device_search_typeahead for discovery. Also includes critical operational guidance: using an org-scoped API key (global keys may return 403) and noting that the org is scoped automatically.

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