Geppetto Robot Directory

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the return shape ('a comparison URL and key differences'), which is valuable given there is no output schema, but it says nothing about read-only nature, error behavior for invalid slugs, or whether the two robots must be distinct.

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, zero filler, with the core action front-loaded before the return-value note. Every clause 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 two-parameter read tool with no output schema, the description covers the action and the return content adequately. Minor gaps remain around failure modes and whether slugs are validated, but nothing an agent needs to invoke it correctly is missing.

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%, with both robot_a and robot_b documented as slugs. The description adds no format, ordering, or constraint details beyond the schema, so the baseline 3 applies.

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 ('Compare two robots side by side') and enumerates the comparison dimensions (specs, price, capabilities). It is clearly distinct from get_robot and search_robots in function, though it never names those siblings explicitly to reinforce the distinction.

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 implied by the phrase 'side by side,' which tells the agent this is for head-to-head evaluation of exactly two robots. However, there is no explicit guidance on when to prefer this over calling get_robot twice, nor any prerequisite (e.g., both slugs must exist).

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 full behavioral burden. It does disclose one useful trait — only 'active' robots are returned — but says nothing about pagination, result-size limits, ordering, or permissions for what is clearly a list-returning read.

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 with the action front-loaded. The second sentence largely restates the first ('Get all robots in a category' / 'Returns the full list of active robots in that category'), consuming space without adding much.

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 no output schema, the description must describe returns; it does so only loosely ('specs and prices', 'full list of active robots'). For a list endpoint, missing details on pagination, ordering, and empty-result behavior leave real gaps.

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% and the slug examples (humanoid, cleaning, lawn, aerial, etc.) are already enumerated in the schema, so the description cannot add much. It adds no format or validation detail beyond what the schema states, making the baseline 3 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?

States a specific verb and resource ('Get all robots in a specific category') plus the payload ('with specs and prices'), which is enough to separate it from get_robot (single robot) and get_component_category (components). It does not explicitly contrast with search_robots, so it stops short of a 5.

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?

There is no when-to-use guidance and no mention of the obvious alternative, search_robots. The agent must infer that this is the category-browsing path rather than a keyword search, and there is no when-not condition at all.

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 full burden, and it does disclose the returned content in detail (bottleneck risk, China concentration, supplier counts, each supplier) — valuable since there is no output schema. It does not state read-only/auth characteristics explicitly, but the 'Get ... by slug' phrasing and payload make the read-only nature clear. No rate-limit or caching behavior mentioned.

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?

One front-loaded sentence: verb+resource+lookup key first, then the returned payload as a compact list. Every clause earns its place, though the trailing enumerations make it slightly run-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?

For a simple one-parameter read tool with no output schema and no annotations, the description supplies the missing return-value information (risk metrics, counts, supplier list) so an agent knows what it will receive. Minor gap: no guidance on relating this to the sibling get_category/get_supplier tools.

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% and the single parameter's schema already enumerates all valid slugs. The phrase 'by slug' adds no syntax or format detail beyond the schema, so baseline 3 applies.

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?

Specific verb+resource: retrieves a robot hardware component category identified by slug, and explicitly enumerates the payload (supply-chain risk, China concentration, supplier counts, supplier list). It is distinguishable from get_supplier (single supplier) and roughly from get_category, though it never states how it differs from that sibling.

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 implied by the payload description: call this when you need supply-chain/bottleneck analysis for a component type. There is no explicit when-to-use vs. get_category or get_supplier routing, and no exclusions or prerequisites stated.

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 full disclosure burden. It usefully characterizes the return as the "full record" and enumerates what that includes, but says nothing about auth requirements, error behavior for unknown slugs, or whether results are cached/static.

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?

One sentence, front-loaded with the verb and resource, with the returned field list appended compactly. No filler, no redundancy, nothing to trim.

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?

There is no output schema, and the description compensates by enumerating the returned fields (specs, license, access type, collection method, citation, source links). For a one-parameter read tool this is close to sufficient; only failure modes and auth expectations are unaddressed.

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 single slug parameter is already fully documented with example values. The description restates the slug-based lookup without adding format, casing, or validation detail beyond the schema, making 3 the correct 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 gives a specific verb and resource ("Get the full record for a specific robot training dataset") and pins the lookup key ("by slug"), which functionally separates it from search_datasets. It stops short of naming the sibling it is not, so the differentiation is implied rather than explicit.

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?

Use is only implied: fetch the complete record when you already have the slug. There is no statement of when to prefer this over search_datasets, nor any precondition such as requiring a known slug from a prior search.

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, and it does add real context: the 0-100 range, the direction of the scale, and the underlying data sources (IFR, Oxford, McKinsey). It says nothing about auth requirements, rate limits, or what happens when a profession slug is unknown, so the behavioral picture is only partial.

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 tight sentences, front-loaded with the score and its range, followed by the interpretation of the scale and the data provenance. No filler or restatement of the tool name.

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 no output schema, the description must explain returns, and it does: the score value, its range, its direction, and the composite data sources. It omits error behavior for invalid slugs and any response-shape detail, which is a minor gap for a single-parameter read tool.

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?

There is a single parameter and schema description coverage is 100%, so the schema already documents the slug format with concrete examples. The description adds no syntax or formatting detail beyond that, making the baseline 3 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?

States a specific verb (get) and resource (Geppetto Robot Impact Score for a profession), and the profession-focused domain is unmistakably distinct from every sibling, which all deal with robots, suppliers, components, or datasets. An agent can route to it 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?

Usage is implied by 'for any profession' and by the score's meaning, so an agent can infer the lookup scenario. However, there is no explicit when-to-use, no when-not-to-use, and no mention of alternatives such as compare_robots for multi-role comparisons.

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 usefully discloses the return payload (specs, price, brand, description, features, URL) and the read-only nature is strongly implied by 'Get'. However, it says nothing about authentication, missing-slug/404 behavior, 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 short sentences, front-loaded with the action and lookup key, followed by the return contents. Every clause earns its place with 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?

For a simple single-parameter lookup with no output schema, the description compensates by enumerating what is returned, and the sole parameter is fully documented in the schema. Minor gaps: no error/miss behavior and no routing guidance to search_robots.

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 itself supplies concrete slug examples, so the description's 'by its slug' adds no syntax or format detail beyond structured data. Baseline 3 applies when the schema does the heavy lifting.

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 (get) and resource (robot) with the lookup key (slug) and enumerates the returned content. It is clearly a single-item detail fetch, distinguishable from search_robots by 'by its slug', though it never names the sibling explicitly.

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 implied: use this when you already have a slug for one specific robot, versus search_robots for discovery. No explicit when-to-use/when-not statement or named alternative, so it stays at the minimum-viable level.

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 full behavioral burden. It usefully enumerates what the returned record contains (components, OEM relationships, country, stock code, bottleneck risk, sources), but says nothing about behavior on a missing/invalid slug, authorization needs, 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?

A single front-loaded sentence that leads with the action and identifier before listing the returned fields. The field list is long but each item is a distinct piece of record content, so little is wasted.

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 no output schema, the description does the work of telling the agent what comes back, listing the record's contents, and a 1-param read tool needs little more. The main missing piece is failure behavior for an unknown slug and cross-reference to search_suppliers.

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% and the slug parameter already carries concrete examples (harmonic-drive-systems, leaderdrive, nabtesco, catl). The description reinforces that the lookup key is a slug but adds no format, casing, or resolution detail beyond the schema, so the baseline 3 applies.

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 (get) plus resource (full supplier record) and scopes it to a single supplier identified by slug, which implicitly separates it from the list-style search_suppliers sibling. It never names that sibling explicitly, so the differentiation is inferred rather than stated.

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 'by slug' phrasing implies you must already know the slug, which is mild usage guidance, but the description never says when to reach for this over search_suppliers or that search_suppliers is the way to obtain a slug. No exclusions or prerequisites are given.

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 does disclose the result shape (name, slug, platforms, modalities, episode count, hours, license, access type, URL) and the corpus size, which helps. It says nothing about pagination, result limits, or ranking, which matters for a search tool.

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 purpose and filter dimensions come first, with the return shape trailing, which is the right front-loading.

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 no output schema, the description usefully enumerates the returned fields, and all six optional parameters are schema-documented. The remaining gap is operational detail (pagination, result caps, whether filters AND-combine), which a search endpoint normally needs.

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 every one of the six parameters is already documented in the schema. The description names some of the same facets (platform, modality, license, commercial-use) without adding format, default, or combination semantics, so baseline 3 applies.

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 resource (Geppetto's directory of 550+ robot training datasets) plus the filter facets. It does not explicitly contrast itself with the sibling get_dataset, which retrieves a single dataset, so an agent must infer the search-vs-lookup split.

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 facet list implies a filtered-discovery use case, but there is no explicit when-to-use or when-not guidance and no named alternative (get_dataset for a single record, search_robots for hardware). Usage is inferable rather than stated.

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 usefully discloses the return fields (name, slug, category, brand, price range, key specs), which partially compensates for the absent output schema, but says nothing about result limits, pagination, ranking, or what happens with zero parameters.

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 tightly written sentences: the search scope is front-loaded and the return payload follows. Every clause earns its place with 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?

For a read-oriented search tool with no output schema, the description supplies the return field list and the queryable facets, which is most of what an agent needs. Only result volume/pagination behavior and safety assumptions are left unstated.

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, category, and maxPrice thoroughly, giving a baseline of 3. The description adds no format or syntax detail beyond the schema, and notably cites 'brand' as a facet although no brand parameter exists (it must be folded into 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 resource (Geppetto's directory of 800+ robots) plus the dimensions filterable. It does not name or contrast with siblings like get_robot or search_suppliers, so an agent must infer the boundary itself.

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 it applies by listing search facets (category, brand, price range, use case), but gives no explicit when-to-use/when-not guidance and never mentions the alternative get_robot for fetching a single known robot.

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 full burden. It usefully enumerates the return fields (name, slug, category, country, listing/stock code, bottleneck risk), but says nothing about result limits, pagination, whether filters combine with AND/OR, or auth requirements for a 140+ item directory.

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 resource and scope, followed by the return fields. No filler or repetition of the tool name.

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 no output schema, listing the returned fields is genuinely valuable and largely compensates. The remaining gap is behavioral: no mention of result limits, pagination, or how the three optional filters interact when combined.

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 all three parameters in detail (including ISO-2 mappings and example slugs). The description only restates the search axes and adds no syntax or combination semantics beyond the schema, so the baseline of 3 applies.

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) plus the concrete resource (Geppetto's directory of 140+ robot hardware component suppliers) and the three search axes. The domain is clearly distinct from search_robots, search_datasets, and get_supplier, so an agent can route without opening a 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 description implies when to use it by naming the searchable facets (category, country, keyword), but never states when-not to use it or points to alternatives like get_supplier for detail lookup. Usage is inferable rather than explicit.

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