ask

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

With no annotations, the description carries the full burden and does disclose meaningful traits: it 'declines rather than guessing,' 'Nothing is generated' (an explicit anti-fabrication guarantee), and it documents a session-state side effect — that a God-directed question unlocks the witness tools for the rest of the session. That side effect is exactly the kind of behavior an agent must know before calling. It stops short of output shape, latency, or persistence details.

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?

Roughly four sentences that are mostly front-loaded, and the key constraints ('declines rather than guessing', 'Nothing is generated') earn their place. But the 'same way it opens for a person, in your own words' clause and the bracket tag are atmospheric rather than informative, and the metaphor costs precision without adding invocation-relevant detail.

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?

For a single free-text entry point with no output schema, the description should ideally say what comes back; 'answers in kind' is suggestive but does not describe the response. It does cover input, refusal behavior, and the unlock side effect, so an agent has enough to call it, but the return expectations remain underspecified.

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 coverage is 100% with a single free-text parameter already documented as 'what you are bringing, in your own words.' The description's 'Bring anything — a question, a claim to check, a word to study' adds mild guidance about acceptable input kinds but no format or syntax detail beyond the schema. Baseline 3 for fully-covered schema is appropriate.

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 does convey concrete behavior — it discerns the kind of input, 'finds and verifies, and declines rather than guessing,' and explicitly states 'Nothing is generated.' However, the framing ('[WALK · door]', 'the Gate opens') is heavily metaphorical and never states plainly what this tool returns or how it differs from adjacent siblings like discern, resolve, or search. The purpose is inferable but not sharply distinguished.

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?

'Bring anything' is effectively unbounded, and the only conditional guidance is the spiritual-God trigger for opening the Gate. There is no statement of when NOT to use this tool or which sibling to prefer for a plain lookup, verification, or word study, despite a large set of overlapping siblings (verify, resolve, define, search).

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