Get Camera State

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

Annotations are absent, so the description carries the full burden. It discloses the confidence levels (OBSERVED, KNOWN_BUT_STALE, UNKNOWN) and their meanings, which is critical behavioral information about data freshness and reliability. It also warns about stale data. However, it doesn't specify the exact return structure beyond 'most recently observed value with confidence metadata', which might be partially covered by the output 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?

The description is reasonably concise, with a clear first sentence stating purpose, followed by confidence level explanations and usage guidance. The structure is logical, front-loading the core purpose and then detailing the confidence semantics. Could be slightly shorter by merging some sentences, but it's well-organized.

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 (confidence levels) and the presence of an output schema (which may define return format), the description covers the critical aspects: what it returns, the confidence semantics, and how to handle stale data. It also points to the sibling for discovering valid settings. The only minor gap is lack of explicit mention of parameter values or examples, but the pointer to list_camera_capabilities mitigates that.

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%, meaning the schema only provides types (string) without any descriptions. The description adds semantics by referencing 'camera capability' and 'setting', but doesn't elaborate on what values are valid beyond pointing to list_camera_capabilities. It partially compensates for the lack of schema descriptions but doesn't fully define parameter meanings.

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 retrieves the current observed state of a camera capability, with 'camera' and 'setting' parameters. It distinguishes itself from siblings like list_camera_capabilities and set_camera_value by focusing on state retrieval. However, it doesn't explicitly state it's a read-only operation compared to set_camera_value, though the context implies it.

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 advises when to use this tool versus others: 'Use list_camera_capabilities to discover valid settings' and warns not to treat KNOWN_BUT_STALE as current, suggesting wait_camera_state for fresh state. This provides clear routing and usage context.

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