Loupe: free citation lookup

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description need only add context. It usefully scopes verification to 'the sources Loupe checks' and discloses the pin-cite range check, but says nothing about coverage limits on those sources or behavior on unrecognized input.

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?

A single dense sentence that leads with the action and lists the three outputs before adding input guidance. Every clause earns its place, though the run-on construction slightly reduces scannability.

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 values need no explanation, and the description covers purpose, input form, and the pin-cite check. The one gap is what happens when no source match is found, but the definition is otherwise sufficient for correct invocation.

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?

One required string parameter with 0% schema description coverage, so the description must compensate. It does: 'Give it exactly as written, with the case name and year if the document has them' tells the agent what the string should contain and that it may hold multiple citations in a sentence. No format examples or length limits are given.

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 (check) and resource (a US legal citation), and enumerates the three things it reports: existence in Loupe's sources, which case it is, and whether a pin cite falls within the opinion. This clearly separates it from the only sibling, search_cases.

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?

Gives concrete input guidance (submit as written, include case name and year when the document has them) and names the failure mode it guards against (a real citation attached to the wrong case). It never explicitly states when to use this versus search_cases, so a 4 rather than 5.

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

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely new context with 'A case missing from the results may still exist' – a coverage/recall limitation an agent could not infer from the structured fields.

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?

Three short sentences, front-loaded with the primary search action, then inputs, then the caveat. Every sentence adds information; nothing is redundant.

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 values need no explanation, and annotations cover the safety profile. The description covers both invocation modes and discloses the recall limitation, leaving nothing an agent needs 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 0%, so the description must carry the load, and it does reasonably: 'query' is explained as parties' names or a citation, and 'year' as optional ('if known'), matching its empty-string default. It stops short of any format or syntax detail.

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 specific verbs and resources: search case names in Loupe's index, or look up the case a citation names. That gives the agent two clear modes and hints at the distinction from check_citation, though it never names the sibling or draws the boundary 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?

It tells the agent what to supply ('the parties' names, and the year if known') and adds a recall caveat, which implies usage. It does not say when to prefer check_citation over this tool, nor state any exclusions, so guidance is implied rather than explicit.

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