Patent by Ouroboros Apps

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

Annotations already cover read-only/idempotent/open-world, so the bar is lower, and the description adds real behavioral context: the provenance of the citation data and the significant limitation that the PatentsView citation graph is paused, implying possible gaps. It does not describe result volume or pagination, keeping 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?

Three tight sentences, front-loaded with the core action, followed by a data-availability caveat and a legal disclaimer. Every sentence carries information, though the disclaimer is the least load-bearing element.

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 read-only, fully-documented two-parameter list tool with no output schema, the description covers scope (US patents), source coverage, and the paused-graph limitation. Return-value details are not needed since the schema and annotations carry the rest.

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 already explains citing/cited_by/both, so the schema does the heavy lifting. The description restates the two directions but adds no syntax or formatting detail beyond what the schema provides; baseline 3 is appropriate.

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?

Specific verb ('List') plus resource ('documents cited by a US patent and documents that cite it') and even names the data sources (USPTO grant references, office-action citations). An agent can tell this is a citation-graph tool, distinct from get_patent and search_patents, though it never explicitly contrasts itself with search_prior_art.

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?

No when-to-use or when-not-to-use guidance relative to the siblings, and no prerequisites stated. The 'PatentsView citation graph is paused' note is a data-coverage caveat rather than routing guidance, and 'Not legal advice' is a disclaimer, not usage instruction.

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 readOnlyHint, idempotentHint, openWorldHint and non-destructive behavior, so the safety profile is covered. The description adds genuinely non-covered context: missing text is omitted rather than filled in (important for an agent interpreting sparse results) and that output is not legal advice. It does not mention rate limits, auth, or failure behavior for an invalid number.

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 action and returned fields, then the omission caveat and disclaimer. No filler or repetition; every sentence carries information.

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 usefully enumerates the returned fields, and the single required parameter is fully specified in the schema. It is nearly complete; only error/invalid-number behavior is unspecified, a minor gap for a simple single-parameter lookup.

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 patentNumber field already documents accepted formats ('US10000000 or 10000000') with length bounds. The description adds only that the target is a US patent, which is already implied by the schema example, so it does not go beyond the schema. Baseline 3 is appropriate.

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?

Specific verb ('Fetch') and resource ('one US patent') plus an enumeration of what is returned (title, abstract, claims, status, family, citations) and the source (USPTO). The singular 'one US patent' implicitly contrasts with the search_* siblings, but no sibling is named explicitly, so differentiation is left to inference.

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 implied: this is the lookup-by-identifier tool, so an agent infers it is used when it already has a patent number, versus the search siblings that discover them. There is no explicit when-to-use, when-not-to-use, or named alternative, and 'Not legal advice' is a disclaimer rather than routing guidance.

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 readOnlyHint, idempotentHint, openWorldHint=false-equivalent safety profile, so the bar is lower. The description adds data-provenance context ('Every number in the result was returned by USPTO') and a liability disclaimer, but says nothing about result ordering, whether more hits exist beyond the limit, or truncation behavior.

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, with the capability statement front-loaded and no wasted clauses. The provenance and disclaimer sentences are brief, though the disclaimer is boilerplate that occupies limited space for little selection value.

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 read-only search tool whose annotations cover the safety profile, the description is nearly complete. However, with no output schema, it leaves unaddressed how results are shaped or whether the response indicates additional matches beyond 'limit', which an agent would want before setting a limit.

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% across all 8 parameters, so the schema already documents formats like YYYY-MM-DD and the 1-25 limit range. The description's facet list roughly mirrors the schema names and adds no syntax or matching-behavior detail beyond it, so baseline 3 applies.

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 (search public US patent records) and enumerates the searchable facets — keywords, claim language, CPC class, assignee, inventor, grant date. An agent can tell it apart from get_patent or find_patent_citations by the fact that it is a facet-based query rather than a lookup, though no sibling is named 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?

There is no statement of when to use this tool versus search_prior_art, find_patent_citations, or get_patent, and no exclusions or prerequisites. 'Not legal advice' is a liability disclaimer, not usage guidance, so the agent gets no routing help.

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 cover read-only, idempotent, open-world behavior, yet the description adds traits the annotations cannot: results are records 'the offices actually returned' (provenance), ranking 'counts overlapping words' (a rough lexical heuristic the agent must not over-trust), output includes Google Patents links, and the results are not a legal conclusion.

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 action and output, then ranking semantics, then caveats; every sentence carries information. The final two sentences ('It is not a patentability opinion. Not legal advice.') are near-duplicates, a minor redundancy.

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 correctly describes what comes back: closest records the offices returned plus Google Patents links, with an explanation of the ranking basis. It stops short of describing result count, empty-result behavior, or how the maxLength-constrained idea is processed, but is otherwise sufficient.

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%, so 'idea' and 'limit' are fully documented in the schema. The description only restates that the input is an idea description and adds no format, length, or query-construction guidance, so baseline 3 applies.

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: it converts an idea description into a public-patent search and returns the closest matching records with Google Patents links. That is enough for an agent to distinguish it from get_patent or find_patent_citations, though it never names or contrasts the sibling search_patents, which is the closest alternative.

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 implied rather than stated: the input is an idea description, so the agent infers when to reach for it, and the disclaimers ('not a patentability opinion', 'not legal advice') set expectations about interpretation. There are no explicit when-to-use/when-not conditions and no named alternatives, so it clears only the minimum-viable bar.

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