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

With no annotations, the description carries the full behavioral burden and provides meaningful detail: the strobe → emit → seal act, the affine_key return values, period_r's constraint ('never a shear label'), and rejection of floats. The terms themselves are obscure, but the disclosure goes beyond a mere existence statement.

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 compact but densely packed with unexplained technical terms ('UUM-8D reconvergence', 'add-law turn', 'patoshi_expose'), making it hard to scan. It is not overly long, but the structure is a single dense block rather than clearly separated behaviors or modes.

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 tool with 8 optional parameters, no output schema, and no annotations, the description leaves many open questions: what each of A, B, K, op, and source do, what 'seal' means, and what the general return shape is for kinds other than affine_key. The routing and some constraints are covered, but the overall operational contract is incomplete.

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 only 38%, yet the description does not explain A, B, K, op, or source, and it references 'period_r' and 'Q' that are not present in the input schema. It adds some context for kind and implicitly for q_hex/object, but fails to compensate for the low schema coverage across most parameters.

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 identifies a specific operation ('court ingest') with a dispatch mechanism ('kind selects the law') and distinguishes itself from siblings by stating that verify_* tools replay emits and study domains forward to math_court. However, 'generic court ingest' remains somewhat vague and relies on domain-specific jargon like 'strobe → emit → seal' to carry meaning.

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 gives concrete selection guidance: affine_key, qc_* / qma_*, empty kind returns catalog, and explicitly routes named verify_* tools to replay a sealed emit and study domains to math_court. It stops short of an explicit 'when not to use' list, but the alternatives and their conditions are identifiable.

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