Venture Atlas

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

No annotations are provided, so the description must carry behavioral information. It mentions that every field carries source URLs, which is useful, but it omits other traits like read-only nature, auth requirements, or rate limits.

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, front-loaded with the core purpose, then a list of content, and a final note about source URLs. Every word adds value, no 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?

Given no output schema, the description lists many returned fields, giving good context. Minor gaps: no mention of response structure or error handling, but the enumeration is thorough.

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% with descriptions for both parameters. The description adds value by telling users to use 'search_companies' for the slug and noting that includeOverview is 'Large; off by default', which goes beyond schema definitions.

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 specifies 'Full Venture Atlas profile for one company' and enumerates all included components (summary, metrics, milestones, etc.). It implicitly distinguishes from siblings like 'search_companies' (search) and 'latest_news' (news only).

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 use for retrieving a comprehensive profile but does not explicitly state when to use this vs siblings like 'list_upcoming_milestones' or 'latest_news'. No when-not or alternative guidance is provided.

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 burden of behavioral disclosure. It usefully explains the distance metric variants (`distanceKm` vs `distanceAllKm`) and notes that each point is sourced. However, it does not disclose behavior such as the default when no operator is provided, what the full time-series response looks like, or update/freshness semantics.

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 compact and front-loaded, immediately stating the tool's purpose and key metrics. Each sentence adds value: the first defines scope, the second clarifies important distance semantics, and the third explains filtering. No filler 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 description covers the main output aspects and parameter semantics, but with no output schema and no annotations, it leaves some operational gaps. An agent may not know what happens when no operator is supplied, whether multiple operators are returned, or the exact structure of the time-series data. It is adequate but not fully complete for a tool with no structured behavioral metadata.

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 a baseline of 3 applies. The description goes beyond the schema by clarifying the meaning of the `distance` metric, distinguishing paid robotaxi distance from broader autonomy distance, and explaining that filtering is by operator slug or metric name. This adds meaningful semantic context to the 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 clearly identifies the tool as a robotaxi operations time-series tracker covering distance, fleet size, coverage area, and city count. It also distinguishes itself from the sibling tools by focusing on comparable operational metrics rather than company profiles, news, milestones, or search.

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 usage context: it is for comparable robotaxi operations time series and can be filtered by operator slug or metric name. It does not explicitly exclude alternatives, but the framing is specific enough for an agent to know when to select 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?

With no annotations, the description adequately discloses the behavior: it returns a digest of sourced summaries, newest first, and is read-only. No destructive or side effects are implied, and the input parameters for filtering are transparent.

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 three sentences, each serving a purpose: naming the tool, describing the content, and explaining filters. No unnecessary words; front-loaded with identity.

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?

Given no output schema, the description sufficiently explains what the tool returns (summaries with companies, dates). It covers filtering and ordering. Minor gap: no mention of pagination or how to handle multiple pages, but 'limit' parameter implies truncation.

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% with descriptions for all parameters. The description adds context about the digest's content and ordering ('newest first'), which goes beyond the schema. This additional context helps the agent understand the tool's behavior.

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 identifies the tool as a news digest ('Venture Atlas daily news digest'), specifies ordering ('newest first'), and describes the content of each item. It is distinct from sibling tools like 'get_company' and 'list_upcoming_milestones', which serve different purposes.

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 explains how to filter by company or date, implying when to use the tool (to get news). It does not explicitly state when not to use it or mention alternatives, but the context is clear enough for typical use.

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?

Clearly describes scope, inclusion criteria ('announced, still-upcoming'), ordering ('soonest first'), and output content (commitment source and track record). No annotations are present, so the description carries the burden; it is transparent but doesn't mention pagination/limits beyond the 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 short sentences convey scope, sorting, content, and filtering in a clear order; no 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?

A read-only list tool with no annotation contradictions; description covers content, scope, sorting, and filter dimensions. Minor gap: it doesn't mention includeUndated behavior or how results are bounded, but schema covers those.

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?

Description adds only 'filter by company or industry', which maps to two of the four parameters; it doesn't explain limit or includeUndated beyond what the schema already documents. With 100% schema coverage, this is adequate 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 ('List') plus a clear object ('announced, still-upcoming milestones'), along with scope ('across all tracked companies'), sorting ('soonest first'), and content (commitments, source, track record). It clearly signals a cross-company listing view distinct from a single-company detail 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?

States when to use it ('forward-looking view: what each company has committed to next') and mentions filters, but does not explicitly say when not to use it or name alternatives.

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 carries the burden. It explains the matching fields, the slim-record output behavior, the effect of omitting `query`, and the relationship to get_company. It does not explicitly mention read-only semantics or possible ordering/pagination, but the behavior described is clear and non-contradictory.

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 with no filler. The core search behavior is front-loaded, and the alternative routing is placed right after the output behavior, making the description easy to scan and act on.

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 adequate for calling the tool, but there is no output schema and 'slim records with a trimmed brief' is vague about the returned fields. For a search tool, an agent would benefit from knowing what fields appear in the slim record, plus any ordering or pagination behavior beyond the limit default already in the schema.

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 meaningful param context beyond the schema, especially the free-text/industry combination and the behavior of omitting `query`. It does not add much about `limit`, but the schema already documents its constraints.

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 action ('Search'), a clear resource ('companies tracked by Venture Atlas'), and the filtering dimensions (free text and/or industry). It also distinguishes itself from get_company by noting it returns slim records rather than full profiles.

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?

Directly routes the agent to get_company for full profiles, setting an explicit condition for choosing the sibling tool. The instruction to omit `query` to list every company in an industry provides a concrete alternative usage pattern.

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