get_ai_perception_senses

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

With annotations already covering readOnly/idempotent/destructive profile, the description still adds substantial behavior: it reads only the OWN SCS template so inherited components are invisible, non-Sight/Hearing classes return sense_type 'unknown' with no fields, and sense_count 0 is ambiguous between empty config and a non-perceiving AI. These are exactly the caveats an agent needs.

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-loaded with the purpose, followed by scoping caveats and the return shape. Every sentence carries information, though the caveat paragraph is dense and the return-shape sentence spells out fields that could be terser.

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?

No output schema exists, and the description compensates by describing the returned fields (config_class, sense_type, sight/hearing fields, three affiliation filters, sense_count) and the edge cases. It resolves the practical ambiguity of an empty result, so nothing an agent needs is missing.

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 100%, so blueprint_name/blueprint_path/component_name are already documented in the schema, including the alias rationale. The description only implies the OWN SCS component constraint, so baseline 3 applies.

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 (read back) and resource (senses configured on an AIPerceptionComponent template of a Blueprint), and explicitly scopes it as the verification counterpart to add_ai_perception_sense. An agent can distinguish this config-read from runtime siblings like get_ai_perceived_actors 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?

Clearly frames the tool as the verification step for add_ai_perception_sense, which gives strong when-to-use context. It also states when results will be empty or degraded (inherited component not found, unknown config class). It stops short of naming a competing read tool or explicitly excluding runtime-perception use cases.

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