Protoperfect Labs

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds a genuinely non-obvious behavior: on a miss it suggests close matches instead of failing, which tells the agent how to handle imperfect queries. It also lists the returned fields, but that is partly redundant with the output schema.

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 compact sentences, front-loaded with what is returned, followed immediately by the fallback behavior. Nothing is 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?

For a one-parameter, read-only lookup with full annotations and an output schema, the description covers the essentials, including no-match handling. Minor gaps remain around matching rules (case sensitivity, aliases), which are left to chance.

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 parameter with 100% schema coverage, so the baseline is already high. The description still adds value by illustrating the expected term format with two real examples, reducing the risk of the agent passing an ID or a natural-language question instead of a term.

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?

Names a specific verb (return) and resource (Protoperfect glossary definition), and enumerates the payload: category, related terms, source paper. The concrete term examples ("Warranted Agency", "Context Window") make the resource unmistakable versus the document-oriented siblings.

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 resource type: an agent infers this is the tool for looking up a glossary term rather than fetching a document. It never explicitly says when to prefer it over search_documents or get_document, and offers no exclusions.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds only the 'public' qualifier, which implies no auth is needed for exposed content. It says nothing about behavior for unknown/private paths, truncation of long pages, or redirects.

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, no filler, with the core purpose and page scope front-loaded and the invocation detail second. Every clause contributes.

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 one-required-param read tool with rich annotations and no output schema, the description covers purpose and input format adequately. The remaining gap -- how to obtain a valid path, and what happens on large or missing pages -- is minor but real.

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% and the sole parameter already documents the path-or-URL duality. The description's only added value is a concrete example path (/research/warranted-agency), a marginal elaboration over the schema text. Baseline 3 applies when the schema carries the semantics.

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 any public protoperfect.io page as Markdown' -- and enumerates the page families (research papers, docs, glossary, FAQ, Studio, Games, About, legal). That makes the scope unmistakable, though it never distinguishes itself from siblings like define_term (glossary terms overlap) or list_documents.

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 you how to invoke it (pass a path or a full URL) and implies when it applies, but gives no exclusions and never routes to the obvious alternatives. An agent that doesn't already know a path gets no hint that list_documents or search_documents is the way to discover one.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description usefully adds that only 'public' pages are returned, but gives no pagination, ordering, or result-size context.

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, no filler, with the return contents front-loaded and the optional filter second. The parenthetical example lists are long but each earns its place by defining the enum values.

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?

A single optional-param read tool with full annotations and an output schema needs little more; the description covers scope, filter semantics and the shape of a result. Only the lack of routing guidance to the sibling retrieval tools keeps it short of complete.

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 0%, so the description must carry the single enum parameter, and it does: each of research, documentation and company is defined with concrete examples (papers and case studies; architecture, blueprints, glossary, FAQ; home, Studio, Games, About). That is real meaning beyond the bare enum list.

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 ('List public pages') plus what each item carries (titles, URLs, summaries). It does not explicitly distinguish itself from search_documents or get_document, so sibling differentiation is left to the name alone.

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?

The word 'Optionally' makes clear the section filter is not required, which implies the no-arg case is a full listing. However, it never says when to use this versus search_documents or get_document, nor any exclusion or prerequisite.

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 readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral detail beyond that: strict AND semantics across all query words, a hard result cap of 12, and that each match returns the best-matching section plus a snippet. It stops short of noting pagination or ranking behavior, so not 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?

Two compact sentences, zero filler. Scope is front-loaded and the matching rule and result shape follow in order of importance.

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 an output schema present, return values need not be explained, and the description still summarizes the result shape. Safety is covered by annotations. Minor gap: no mention of whether ordering/ranking or phrase vs. token matching beyond the AND rule.

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% and the single query parameter is documented (up to 160 characters). The description adds genuine semantic meaning the schema lacks: that matching requires every word to appear, which materially shapes how an agent should phrase the query.

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 (Search) and the exact corpus (Protoperfect Labs research papers, documentation, blueprints). The verb 'search' naturally distinguishes it from siblings get_document and list_documents, so an agent can route without opening the schema.

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?

The AND-matching rule ('Every word of the query must appear') implies when this is appropriate for multi-term lookup, but there is no explicit when-to-use versus list_documents or get_document, nor any stated exclusions. Usage is only implied.

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