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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description clears it by disclosing provenance and reliability: deterministic vs AI-reviewed outcomes, null when the corpus cannot tell, and an explicit warning that decided_for_provision=false may be wrong for articles inserted or deleted mid-life. It does not cover latency, result shape stability, or what to do on errors, which keeps it short of a 5.

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?

Front-loaded with the core question, then progressive detail about edge cases; no filler sentences. The telegraphic, backtick-heavy fragments ("`source: 'no_force_event'`: none ever recorded -- read `document_status_name`.") are efficient but read like notes rather than prose, slightly raising parse cost.

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?

With no output schema, the description carries the return-value burden and does name the key fields (in_force, outcome, scope, version_in_force_urn, decided_for_provision, source, document_status_name) along with their interpretation. It stops short of enumerating all possible `outcome` values or the full `source` set, leaving some guesswork for a tool whose output is otherwise undocumented.

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% for both parameters, so the baseline is 3. The description does add real meaning to `urn` by explaining that an undated URN asks about the provision while a dated one asks about that version of its text, but it says nothing about the `date` parameter's format, timezone, or boundary behavior.

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?

States a specific verb-and-resource pair: testing whether one legal unit was in force on a given date. An agent can distinguish this from get_unit (content) and get_unit_editions (history) without opening the schema, though the description never names those siblings explicitly.

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?

Usage is only implied by the first sentence; there is no explicit when-to-use / when-not guidance versus get_unit_editions or get_unit_fulltext. The undated-vs-dated URN rule is useful routing guidance for choosing the urn form, but it addresses parameter selection rather than tool selection.

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