Clearly

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

With no annotations, the description carries the burden and does disclose meaningful behavior: no auth required, the agent has owner-curated context, and sessionId preserves conversation memory. However, it does not disclose return format, potential side effects of the visitor object, or whether the conversation can have persistent external effects—so behavioral transparency is adequate but not rich.

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 sentences, each earning its place: the first defines the tool's purpose, the second adds auth/context details, and the third gives workflow and memory guidance. The description is front-loaded and free of filler.

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 description is sufficient for a conversational tool with a small parameter set: it explains how to find the slug, what to send, and how to maintain memory. Missing details like exact return format are partially covered by 'answers questions in natural language,' and the visitor object is well documented in the schema, so the gap is minor.

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%, so the baseline is 3. The description adds value beyond the schema by tying publicSlug to 'clearly_search_projects results' and clarifying that sessionId should be stable 'across calls to keep conversation memory.' This practical guidance supports correct invocation.

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: 'Talk to a public Clearly project's AI agent,' and clarifies the agent answers questions using owner-curated context. It also implicitly differentiates from siblings by describing discovery ('discover projects' in clearly_search_projects) as separate and this tool as the follow-up conversation step.

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 gives clear usage context: pair with clearly_search_projects to find projects, then ask follow-ups here, and reuse sessionId for memory. It does not explicitly state when not to use this tool or mention the clearly_capture_lead sibling, so it falls just short of full exclusion 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the owner receives a notification with contact details, that no auth is required, and that contact info is required for follow-up. This gives enough operational transparency for the agent to anticipate side effects. It could add what happens on failure, but core behavior is clear.

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. The main intent and trigger are front-loaded in the first sentence, and the second gives behavior and prerequisite signal. Every clause contributes directly to correct invocation.

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 definition is structurally adequate for a simple notification-capture tool: it identifies when to call it, what happens, and the required data. It could enrich the picture by mentioning how publicSlug maps to the target project or noting optional conversationId linking to clearly_ask_project, but the siblings are implied by schema and naming. Given no output schema and reasonable annotation support, that edge is not fatal.

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 60%, which is moderate. The description adds meaningful guidance about the contact object (email/phone required) beyond the schema, but it does not clarify publicSlug's purpose or which fields of contact are actually needed beyond the requirement. It adds some value but does not fully compensate for the uncovered parameters.

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 ('Tell') and resource ('Clearly project owner'), and explains exactly when to invoke it: when the visitor signals real intent (meeting, demo, pricing, tour, purchase). This clearly distinguishes it from siblings like clearly_ask_project by narrowing the trigger to lead-capture behavior rather than generic questions.

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 explicit when-to-use guidance: 'Use when the visitor signals real intent'. It also notes prerequisites (visitor email/phone required) and that no auth is needed. However, it does not explicitly name alternatives or state 'do not use for general inquiries', so it stops short of a full when/when-not/alternative rubric.

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 full behavioral burden. It discloses that the search is over public projects, requires no authentication, returns ranked matches, and each result includes a public_slug for use with clearly_ask_project. It does not describe error cases or full result fields, but for a read-only search tool this is substantial transparency.

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 with no filler: the opening sentence states the resource and scope, and the second sentence covers the return value and its connection to the sibling tool. Every sentence earns its place.

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 3-parameter search tool with no output schema, the description provides enough to invoke correctly: what is searched, that no auth is required, that results are ranked, and how to chain into clearly_ask_project. It would be more complete with a note about result shape or limit behavior, but those are minor gaps for this tool's complexity.

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 the schema already documents query, limit, and category. The description adds context about categories and public projects, but does not materially extend parameter semantics beyond what the schema provides, so 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?

The description uses a specific verb ('Search'), a specific resource ('the Clearly directory of public projects'), and enumerates example categories. It clearly distinguishes the tool from clearly_ask_project by explaining that results include a public_slug intended for that sibling 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 gives clear context: use this to search public projects, and then use clearly_ask_project to chat with a project's AI agent via the returned public_slug. It notes 'No auth required,' which helps an agent decide it can invoke this safely, though it does not explicitly state when not to use it or mention clearly_capture_lead as an alternative.

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