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

With no annotations, the description carries the full burden. It discloses useful behavior: outputs returned (patoshi_expose, shors_qmt_witness, topological_shear), a verdict (jordan_proven), an input constraint ('Floats refused'), and that no k is used for affine_key. Missing: permissions, side effects of 'seal', idempotency, and error/refusal behavior beyond the float check.

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?

It is a single front-loaded paragraph with no filler sentences — mode routing, output keys, verdict, and the float constraint are packed efficiently. Density of unexplained jargon slightly harms readability, but no sentence is wasted.

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 an 8-parameter, no-output-schema, no-annotation tool, the description does cover return values and mode routing, which is the right burden to carry. It falls short of telling an agent how the lattice/lock inputs combine or what 'seal' produces in most modes, leaving the calling contract unclear.

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%, so the schema already documents A, B, K, op, kind, q_hex, object and source; baseline is 3. The description adds marginal meaning by tying kind values to modes and mentioning period_r (which is absent from the schema), but it does not clarify the actual semantics of the lattice/lock parameters beyond what the schema already states.

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 header 'Generic court ingest. kind selects the law.' identifies this as a parameterized dispatcher, and the body distinguishes several modes (affine_key, qc_*/qma_*, empty kind, math_court domains). However, it never states plainly what 'expose' does as a tool; the purpose is buried in opaque metaphor ('strobe → emit → seal') that an agent cannot decode without prior 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?

It does route to alternatives — 'Named verify_* tools replay a sealed emit' and 'Study domains forward to math_court' — which is genuine when-to-use guidance against siblings. But it never states when to choose expose over, say, lattice_op or project_affine_key, and there are no explicit exclusions or prerequisites beyond 'Floats refused'.

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