docracy

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

The phrase 'Look up' implies a read-only operation, but the description does not explicitly state that it has no side effects, nor does it mention authentication requirements, error behavior, or what happens with invalid links. Since annotations are absent, the description carries the burden and covers the basic read-only nature but lacks deeper behavioral disclosure.

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?

The description is a single, front-loaded sentence that directly states the action and the information returned. It contains no fluff or redundant wording, making it highly concise and well-structured.

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 status-lookup tool with one parameter and no output schema, the description sufficiently explains the outcome ('who's signed, who's still pending'). It lacks details on exact response formatting or edge cases, but given the simplicity, it covers the essential context.

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?

The schema already provides 100% coverage for the 'link' parameter, describing it as a docracy.io sign/status link or token. The description's mention of 'from a sign or status link' aligns with the schema but does not add additional semantic meaning beyond what the schema already states, so the baseline score of 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?

The description uses the specific verb 'Look up' and identifies the resource as 'status of a Docracy signing chain,' making the tool's purpose unmistakable. It also adds context that it works from a sign or status link, which further clarifies its scope.

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 description clearly implies when to use the tool: when you have a sign or status link and need to know who has signed and who is pending. There are no explicit exclusions or alternatives, but the context is clear and self-contained.

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?

With no annotations, the description carries the burden of disclosure. It honestly discloses that the tool returns specific artifacts (prepare URL, library page, drafting hints), that it does not trigger sending, and how optional notes are used. It does not detail side effects like whether a server-side draft or library record is created, but the important workflow behavior is covered.

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?

The description, composed of three sentences, delivers the core purpose, return values, a safety-relevant limitation, and a parameter behavior without any filler. Every sentence contributes to a clear mental model.

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?

Because there is no output schema, the description correctly lists the returned artifacts and mentions the human-review workflow. It makes proper mention of the source of the slug in a later schema, but doesn't describe error conditions or whether the operation requires prior authentication or consent. For this scope of description, it is largely 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?

Both parameters are fully described in the input schema, so the baseline is 3. The description adds minor context by mentioning that notes are echoed as 'a drafting brief for the assistant,' but it does not substantially extend meaning for the slug parameter. The schema's example (mutual-nda) already provides the needed orientation.

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?

The description explicitly states a specific action and resource: 'Start an agentic drafting workflow from a trusted Docracy template.' It also differentiates the tool's scope by enumerating distinct returns (prepare URL, library page, drafting hints) and by clarifying that it does NOT auto-send, which distinguishes it from an end-to-end signing tool.

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 description provides clear use context: use it when you want to start a template-based drafting workflow, and not when you need to send for signature — the human sends afterwards. It implies the slug should come from referring to list_templates, but it does not explicitly name alternative sibling tools or state exclusions beyond not-auto-send.

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?

No annotations are provided, so the description bears the full burden. It discloses that the tool returns metadata and a prepare URL, implying a read-only operation, but it does not explicitly confirm whether any mutation occurs (unlikely) or whether authentication/authorization is required. It also does not state that the prepare URL is generated (possibly a side effect) or its validity duration, leaving some ambiguity for an agent.

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?

The description is a single efficient sentence that covers what the tool fetches, the input parameter, and the extra return value (prepare URL). It is front-loaded with the core action and resource, and every phrase earns its place, with no fluff or repetition.

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?

The tool is simple: one input parameter, no output schema, and no annotations. The description adequately covers the input and the shape of the output (metadata + prepare URL) but does not specify the exact return format (e.g., JSON structure) or error cases (e.g., what happens if the slug is invalid). For a simple fetch operation, this is acceptable but not comprehensive.

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?

The schema description for the slug parameter is already very helpful: it provides an example and guides the agent to use slugs from list_templates. The tool description adds the context that the slug identifies a specific template for metadata retrieval, but that is largely redundant with the schema. Since schema coverage is 100%, the description does not add significant new semantic value beyond the schema.

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?

The description clearly states a specific action: fetch metadata for one Docracy template by slug, listing the metadata fields (title, description, key clauses/drafting hints) and the prepare URL. It is distinct from siblings like list_templates (which lists templates) and draft_from_template (which likely creates a draft), so an agent can tell them apart.

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 description implies usage by specifying a single slug as the input and referencing the sibling list_templates as a source for slugs ('a Marketplace slug from list_templates'). It does not explicitly discuss when not to use this tool versus list_templates or draft_from_template, but the contextual detail—metadata retrieval vs listing vs drafting—provides sufficient implied context.

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?

With no annotations provided, the description carries the full burden of behavior disclosure. It states the tool returns slugs and prepare URLs, and explicitly says it does not create or send documents. This is meaningful transparency beyond the schema and prevents the agent from treating it as a write action.

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 short sentences that front-load the tool's purpose and immediately follow with the optional filter and return behavior. No fluff, no repetition of schema details, and every sentence adds 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 single-parameter list tool with no output schema, the description sufficiently covers what results to expect (slugs and prepare URLs), the available content (free and Marketplace templates), and the safety profile (creates or sends nothing). No critical gap remains.

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 schema already explains the query parameter with examples. The description adds only a slight reminder to omit the query to list popular templates, but it does not materially extend the schema's meaning. It is adequately covered but not enriched.

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?

The description uses a specific verb and resource: 'List free and Marketplace legal templates from Docracy,' with concrete examples like NDAs and offer letters. It also distinguishes itself from siblings by noting it does not create or send documents, and the output is only slugs and prepare URLs.

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 description clearly indicates when the tool is appropriate: browse or search templates with an optional text query, and omit query to list popular templates. It does not name alternatives like draft_from_template or get_template, but it clarifies this tool is read-only, providing enough context to avoid misuse.

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