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

With no annotations provided, the description carries the full behavioral burden, and it delivers: it explicitly states the tool is deterministic, does NOT perform ECDLP (no scalar search), refuses malformed input (REFUSED family) and floats, and details the computational law (scalar multiplication A*G, total, no search). For an unannotated tool this is genuinely useful behavioral disclosure, only slightly hampered by the cryptic vocabulary.

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 dense wall of run-on, jargon-packed sentences ('q_hex ALONE answers UNPRESENTED_PAIR - no scalar on the wire; x(Q) is reported as ground because it is real and derivable, and it is PUBLIC, never a face'). While information-rich, it is not front-loaded or structured for rapid parsing; the esoteric terms force an agent to decode multiple domain-specific concepts before acting.

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 (a multi-step pipeline), the absence of an output schema, and zero annotations, the description covers many aspects: input handling, result families (UNPRESENTED_PAIR, pair_verdict, sig_ready, pack_lock), edge cases (malformed, floats), and determinism. Yet its completeness is undermined by unexplained specialized vocabulary — an agent unfamiliar with 'court', 'face', 'ground', and 'pack_lock' cannot fully exploit the information provided.

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%, but the description adds real value beyond the schema: it clarifies that q_hex is the primary/required input (the schema lists no required params yet q_hex's description says 'required'), that Q is an alias for q_hex and k is an alias for A ('same face'), and specifies format constraints (04-prefixed uncompressed pubkey hex; A as 64-hex or decimal). This resolves ambiguity the schema alone leaves open.

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 states a clear operation at a high level — fuse an open key (q_hex) with an optional private face (A) and produce a verification verdict (UNPRESENTED_PAIR, pair_verdict WIN). It references siblings project_affine_key and verify_presented_pair by name, aiding differentiation. However, the purpose is buried under dense esoteric jargon ('court', 'FALSE FACE', 'pack_lock', 'ground', 'face'), making it hard for an agent to grasp the core verb without domain knowledge.

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 gives an internal branching rule: q_hex alone answers UNPRESENTED_PAIR; providing A triggers pair verification via the verify_presented_pair law. It also references that the same law project_affine_key runs, hinting at sibling relationships. But it never explicitly tells the agent when to choose THIS tool over verify_presented_pair or project_affine_key — the selection guidance is implicit, not stated.

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