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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description still adds real behavioral context: the source is fetched live, results are never a satisfied/not-satisfied determination, zero relevant cards returns EMPTY rather than an error, and article-53 output is evidence for review only. These edge-case and non-determinism semantics are exactly what annotations cannot convey.

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 dense and front-loads the resource and scope, and each disclaimer (EMPTY semantics, no determination, grants no status) carries load. The third and fourth sentences overlap somewhat in re-stating the non-certification boundary, which is minor redundancy rather than padding.

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?

An output schema exists, so return structure need not be described, yet the description still covers the two cases an agent must handle correctly — zero relevant cards (EMPTY, not an error) and the non-determinative nature of relevance. Combined with the documented enum and subject semantics, nothing needed to call this correctly 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% and the enum values for obligation are fully documented in the schema, so the baseline is 3. The description restates the subject concept ('a model id, vendor or instrument the cards must name') and confirms the obligation-wide selection when omitted, but adds little beyond the schema text.

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 names a specific verb+resource and scope: the obligation record, its counsel-gate status, and the already-signed measurement cards relevant to exactly ONE obligation, read live from a named endpoint. It also constrains the selection to one of four obligations, which separates it from card-level siblings like get_card or list_cards.

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 clear context for use (obligation-level evidence for a single obligation, optionally narrowed by subject) and explicitly rules out use as a conformity assessment, certification, audit opinion or compliance determination. It does not, however, name a sibling tool or state when to prefer this over measurement_index or list_cards, so routing guidance is partial.

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