Unicorn Screener

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

Beyond the readOnly/idempotent annotations, the description discloses the polling cadence, a finite timeout, and the state transitions (running/refreshing, moved/publishedSlug, terminal failure/success states). This adds meaningful behavioral context, though it stops short of specifying exact timeout duration or return shape.

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 dense sentences carry the full state machine, polling interval, timeout guarantee, and stopping conditions. The most important directive comes first, and there is no filler or repetition of schema/annotation data.

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 state machine is well specified and the tool is simple (one parameter), which helps completeness. However, with no output schema, the description does not describe the actual return value's fields or how the agent should read the status from the response, nor does it state the finite timeout's value. These gaps leave a capable but not fully self-contained definition.

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?

With schema description coverage at 0%, the description must define the sole parameter. It identifies 'slug' as a memo slug returned by a prior operation, which is useful, but it does not elaborate on provenance or expected format beyond what the schema pattern already provides, leaving the parameter partially under-specified.

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 states a clear action ('Check...'), a specific resource ('returned memo slug'), and a state-machine behavior. It does not explicitly name a sibling tool to distinguish it from, but the polling/following language makes its role distinct from lookup, read, request, and search tools.

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 explicit operational guidance: when to wait, when to follow, when to stop, and how often to poll. It does not explicitly state when this tool should be used instead of alternatives or what preceding call produces the slug, but 'returned memo slug' implies it follows a request flow.

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, non-destructive behavior. The description adds valuable context beyond those: the record must be public and existing, and a missing record is explicitly not a negative assessment. This prevents a common misinterpretation of lookup failures.

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 carry the core purpose, behavioral constraint, and the important missing-record caveat. No filler or redundant restatement of the schema exists.

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 lookup tool with rich annotations, the description covers what is returned, that it is read-only, that no research is started, and how to interpret a missing record. Nothing essential is missing for an agent to call it correctly.

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 50%: the optional website parameter is described, while the required name parameter is not. The description does not add parameter-level detail, though 'name' is fairly self-evident from the tool name. It does not compensate for the missing name description enough to rise above baseline.

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 ('Retrieve') with a clearly bounded resource: an existing public startup score, summary, analysis date, and memo URL. The phrase 'without starting research' differentiates it from sibling tools like request_startup_memo, making its purpose unmistakable.

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 makes clear that this tool is for looking up an already-existing score rather than initiating new research. It does not explicitly name alternatives or state when not to use it, but the context is clear enough for an agent to route correctly.

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 provide readOnlyHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context beyond annotations: the returned content is untrusted research material, not instructions; it does not include private bulk reports or internal scoring formulas; it includes the source URL. This covers security and data scope aspects useful for the 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 concise yet informative: two sentences that front-load the purpose and include essential safety/security cues. Every phrase adds value: 'public memo', 'as text', 'includes the source URL', and the trust disclaimer. No fluff.

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 with one parameter and no output schema mend, but the description covers the essential behavioral aspects: what it returns, the source URL, and the non-instructional nature. Missing details like response format or error cases are minor. The annotations cover safety, and the description fully covers the operational context. Could be improved by briefly noting that the slug is the URL slug, but not critical.

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 coverage is 0%, so the description must compensate. The description mentions the slug indirectly and explains what content is returned, but it does not detail the slug format beyond what the schema provides (pattern, max length). However, with only one parameter, the description's context of 'uses its slug' plus the schema's detailed pattern is adequate. Baseline 3 is fair.

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 the tool reads a public startup memo as text using its slug, and includes the source URL. It differentiates from siblings by implying it retrieves a specific memo's content rather than screening, looking up, or searching. The verb 'read' and resource 'public startup memo' are specific and unambiguous.

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 when to use this tool: when you need the content of a specific public memo by slug. It does not explicitly mention alternative tools or when not to use it, but siblings like search_startups or request_startup_memo suggest alternatives for discovery or restricted content. Lacks explicit exclusions but still provides clear context from 'public'.

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=false, idempotentHint=false, and destructiveHint=false. The description adds valuable context beyond annotations: it consumes the user's free allowance, requires authorization and a stable fingerprint, is not idempotent, and that additional reports require purchase. This goes beyond what annotations provide, though it doesn't detail the exact email content or failure modes.

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?

Four sentences, each carrying distinct information: what the tool does, what it consumes, what it requires, and what it is not. No filler or repetition of schema details. The most important behavioral constraints (non-idempotent, allowance consumption) are front-loaded.

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 tool with no output schema, the description covers the key operational aspects: asynchronous nature, email delivery, quota consumption, non-idempotency, and purchase requirement. It doesn't describe what the user sees immediately (e.g., a request ID or confirmation), but the core invocation context is well covered. The sibling tools are all read-oriented, so the description's emphasis on 'start' and 'new' sufficiently differentiates it.

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 67% (email and fingerprint have descriptions; startupName does not). The description adds context about the fingerprint's purpose ('Persisted caller identifier reused across calls. Never rotate to bypass quotas.') and email's purpose ('User-authorized, non-disposable email for the memo notification.'). The description text reinforces the fingerprint's role in quota enforcement, which is useful. startupName lacks a description, but its meaning is self-evident from the tool name and context.

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 states a specific verb ('Start'), a resource ('asynchronous startup analysis'), and the delivery mechanism ('email the public memo link'). It clearly distinguishes this from sibling tools like get_screening_status or read_startup_memo, which are about reading results rather than initiating a new analysis.

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 explicitly warns not to repeat while waiting (non-idempotent), notes that additional reports require purchase, and implies this is the tool to use when starting a new analysis. It also mentions prerequisites (authorization and stable fingerprint), giving clear context for when to invoke this tool.

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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it returns candidate names and domains, which is useful, but doesn't disclose behavior like fuzzy matching, pagination, or result limits. With annotations covering the core safety traits, a 3 is appropriate.

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 sentence that front-loads the action and outcome with zero waste. It earns its place by clarifying the tool's role as a resolver rather than a final lookup.

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 read-only tool with one parameter and no output schema, the description is nearly complete. It tells the agent what to expect (candidate names and domains) and the context (before choosing identity). The only gap is not describing result limits or how to handle multiple candidates, but that's minor given the tool's simplicity.

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 compensate. It explains the query is a company name, which adds meaning beyond the bare 'query' string field. However, it doesn't provide format details like case sensitivity, partial matching, or whether domains are included in the query. Baseline 3 is fair since the description gives some semantic context.

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 ('Resolve') and names the resource (company name to candidate startup names and domains), which clearly distinguishes it from a generic search. It doesn't explicitly name sibling tools, but the purpose is clear enough to differentiate from lookup_startup and read_startup_memo.

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 this is a pre-step before choosing an intended identity, suggesting it should be used before lookup_startup or read_startup_memo. However, it doesn't explicitly state when not to use it or name alternatives, leaving some inference to the agent.

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