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

With no annotations and no output schema, the description usefully discloses the shape of the returned string (INSC-first, optional parallel forms, registry-style footnote). It says nothing about failure behavior — what happens when the citation is not resolvable, or whether the tool errors or degrades — which is the main behavioral gap for a transformation tool.

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?

Two sentences, front-loaded with the output description, with no filler. Minor overlap between 'ready-to-paste' and 'standardize citations in drafts' keeps it from being maximally tight.

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 simple two-parameter formatting tool this covers what the output looks like and the intended setting. It leaves unresolved how non-INSC or ambiguous references are handled, which matters because the 'citation' parameter explicitly accepts 'any resolvable reference'.

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 50%: 'citation' is documented in the schema, while 'style' is undocumented beyond its enum values. The description's mention of optional parallel SCC/AIR/SCR/MANU forms loosely maps to 'full_parallel', but it never ties the style options to the enum names, so it adds only partial meaning.

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: 'Return a ready-to-paste citation string' leading with the INSC neutral citation, with optional parallel forms and footnote. That is clearly distinct from resolve_citation, check_treatment, and get_ratio in kind, though the description never names a sibling to make the contrast explicit.

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?

Provides a usage context ('to standardize citations in drafts and pleadings'), which implies when to reach for it. It does not say when not to use it, nor how it relates to resolve_citation for unresolvable references, so an agent must infer the boundary between resolving and formatting.

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