aetumi

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld=false, so the safety profile is covered structurally. The description adds non-redundant context — no authentication required and the return is public metadata — which tells the agent it can call this freely without credential handling.

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: what it returns, what it excludes plus alternatives, then the access/safety profile. Front-loaded with the payload and 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?

With an output schema present, return-value detail is unnecessary, and the annotations already carry the safety profile. The description covers scope, boundaries, alternatives, and auth, leaving nothing an agent needs in order to call a parameterless metadata tool 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly does not waste space re-explaining an empty 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 states a specific verb and resource — it returns what AETumi is, what the platform does, and its canonical links — and explicitly bounds the scope to platform facts. It also names the siblings it is not (search_3d_web_assets, find_experiences, get_pricing), so an agent can distinguish it without opening any 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?

It states when to use this tool (platform facts) and when not to (assets, experiences, prices), routing the agent explicitly to the three alternative tools for each excluded case. This is about as close to a routing table as a description gets.

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, idempotentHint and non-destructive, so the safety profile is covered; the description still adds real behavior beyond them: exhaustiveness vs. ranking, pagination via a returned cursor, the fields each item carries, and 'no authentication, no side effects'. It does not detail ordering of the paged list, but that is minor against the annotation coverage.

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?

Front-loaded with the core behavior, then value list, then routing guidance – logical order with no filler sentences. It runs a bit long, but every clause (category values, return fields, alternatives, safety) carries information an agent would otherwise have to infer.

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 filtered-list tool with a full output schema already defined, the description supplies everything else an agent needs: valid category values, pagination via cursor, exhaustive-not-ranked semantics, and sibling routing. Nothing material 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%, which sets a baseline of 3, but the description goes further by enumerating the accepted category values (3d_scene, template, figma, section, background, gradient, web3d) that the schema lacks as an enum, plus noting case-insensitive exact matching. This is genuine added meaning over 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?

States a specific verb and resource ('Return EVERY AETumi catalog asset in one exact category') and immediately clarifies the semantic mode as 'a complete paged list rather than a ranked search', which distinguishes it from the ranked sibling search_3d_web_assets. An agent can distinguish it from all twelve siblings 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?

Gives an explicit use condition ('when you want the full inventory of a category you already know') plus exclusions and named alternatives: search_3d_web_assets for keywords/ranking, list_3d_web_categories for counts, filter_by_industry/find_experiences for Labs references. When-to-use, when-not, and alternatives are all present.

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, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered; the description still adds useful context beyond that — no authentication required, public catalog metadata only, and that results are paged with a total and cursor. It restates the read-only/no-side-effects traits already in annotations rather than revealing new behavior, so it stops short of 5.

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 scoping statement, accepted-value list, return shape, and routing guidance are ordered sensibly with the key distinction front-loaded. It is on the dense/long side and the return-field enumeration is somewhat redundant with the output schema, but nearly every sentence carries actionable information.

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 an output schema exists, the description needn't explain return values, yet it still summarizes them; with annotations covering the safety profile and the schema covering pagination params, an agent has everything needed to select and invoke the tool 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 100%, so the baseline is 3, but the description goes further by enumerating the accepted industry values (Technology, E-commerce, Biotech · Science, Web3 & Crypto, etc.) — critical because the schema has no enum. The semantics of limit/cursor are left to the schema, which documents them adequately.

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 ('Return EVERY AETumi catalog asset for one exact industry') and explicitly frames the result as a complete paged list rather than a ranked search. It also names the siblings it is not (search_3d_web_assets, filter_by_industry), so an agent can disambiguate without opening any 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?

Gives explicit when-to-use ('the full inventory for an industry you already know') plus the when-not and the exact alternative ('If you only have keywords, or want ranking across industries, use search_3d_web_assets'). It further separates this from filter_by_industry by scope (commercial assets vs AETumi Labs reference experiences), leaving nothing to inference.

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, idempotentHint, and destructiveHint=false, so safety is covered. The description still adds value: 'no authentication, no side effects; returns public metadata' and clarifies these are not catalog items for sale — a distinction that matters for interpretation. It stops short of describing pagination or cardinality limits beyond the stated 31.

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?

Front-loaded with the core behavior, constraints, and routing before the value list. The 19-value enumeration is long but necessary given the absent enum, so it earns its place. Slight redundancy between description and schema on case-sensitivity keeps it from a 5.

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?

An output schema exists, so return-value documentation is optional, yet the description still names the fields returned. Combined with the value list, usage routing, and behavior disclosure, an agent has everything needed to call the tool 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 100% and the schema restates case-sensitivity, but the schema defines no enum, so the description's enumeration of all 19 accepted customer goal values is genuinely load-bearing information not available in structured fields. Baseline would be 3; the value list lifts it above that.

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+resource (return Labs reference experiences matching a customer goal) and explicitly distinguishes itself from find_experiences and search_3d_web_assets. An agent can identify the tool's scope without opening any 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?

Explicit when-to-use ('ONLY when you already hold one of those exact values'), explicit when-not ('if the request mixes customer goal with another facet, or uses wording outside that list'), and names the alternative tools to use instead. This is textbook routing 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds useful context: returns public metadata, no authentication, no side effects, and enumerates the fields each result carries. Slightly redundant with annotations but adds value beyond them.

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?

Well-organized with the core behavior front-loaded, followed by the exact-values list and routing guidance. The sentence about the 31 experiences being reference-only is useful context but slightly verbose; overall tight and purposeful.

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?

Complete for a simple filtered-list tool. Output schema exists, so return values needn't be explained in detail, yet the description helpfully enumerates carried fields. Covers scope, constraints, alternatives, and behavioral profile comprehensively.

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 documents the single parameter well. The description reinforces this by listing all 13 accepted industry values and emphasizing exact/case-sensitive matching, adding meaning beyond the schema example. Strong for a 1-param tool.

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 (Return), resource (AETumi Labs reference experiences), and scope (industry matches one exact value), and explicitly distinguishes what it is not (NOT catalog items for sale). Clearly differentiable from siblings find_experiences and search_3d_web_assets.

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?

Explicit when-to-use ('ONLY when you already hold one of those exact values'), when-not ('fills request mixes industry with another facet, or uses wording outside that list'), and names the alternative (find_experiences). Also routes commercial asset requests to search_3d_web_assets.

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 read-only/idempotent/non-destructive/no-auth-ish safety profile, so the bar is lower; the description still adds that it is read-only, requires no authentication, has no side effects, and returns public metadata plus the exact field set per result. Useful added context beyond the annotations.

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?

Front-loaded with the core action and scope; the alternative-tool routing is efficiently packed into two sentences. The 21-value enumeration is long but necessary for an exact-match filter, and the 'NOT catalog items for sale' clarification earns its place by preventing misuse.

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?

An output schema exists, so return-value explanation is not required, yet the description still summarizes returned fields. Combined with the full usage routing, exclusions, and parameter semantics, nothing an agent needs to call this 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 coverage is 100% and the enum values are listed in the description too, but the text still adds real meaning: case-sensitivity, exact-match-only behavior, no partial word matching, and a pointer to find_experiences for free text. That goes beyond the schema's restated example.

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 (return/list) and resource (AETumi Labs reference experiences) plus the exact filtering dimension (visual style, one exact value). It also contrasts itself with sibling filter_by_* tools and find_experiences, so an agent can pick it out immediately.

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?

Explicitly gives the when ('only when you already hold one of those exact values'), the when-not ('if the request mixes visual style with another facet, or uses wording outside that list'), and names two concrete alternatives: find_experiences and search_3d_web_assets.

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 readOnly, idempotent, non-destructive and non-open-world, so the safety profile is covered. The description adds real context beyond that: ranked (not exhaustive) results, the size of the corpus (31 live reference experiences), and the important caveat that these are study references and NOT catalog items for sale. It does not discuss pagination or ranking algorithm, which keeps it short of a 5.

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?

Front-loads the core action and scope, then routes to siblings, then qualifies the dataset. Every sentence carries information, though the enumeration of return fields (name, industry, styles, goals, urls) is somewhat listing-heavy for a tool that has an output schema.

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?

An output schema exists, so return values need no elaboration, and the description still covers scope, ranking behavior, dataset nature, auth/no-side-effects, and sibling routing. An agent has everything needed to call this 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 description coverage is 100%, so both parameters are already documented, including the limit range and default and the query's mixable facets. The description's example ('dark cinematic automotive launch') largely restates the schema's own example, so it adds little beyond the 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?

States a specific verb and resource (free-text search across the AETumi Labs reference experiences) and names the exact facets searched. It explicitly distinguishes itself from filter_by_industry/filter_by_style/filter_by_goal and search_3d_web_assets, so an agent can route correctly without opening any 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?

Gives an explicit when-to-use condition (requests that COMBINE facets or use non-exact wording, with concrete examples) and explicit alternatives with the condition that selects them (exact facet value → use the exhaustive filter_* tools; commercial assets → search_3d_web_assets). Nothing is left to inference.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds useful context — no authentication required, no side effects, returns public metadata only — though these largely restate the annotation semantics rather than reveal new traits like rate limits or field-level caveats.

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 lookup key and its provenance are front-loaded, and every sentence is functional. It is slightly dense with parenthetical enumerations, but nothing 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?

An output schema exists so return values needn't be described, yet the description still gives a field preview. Combined with the explicit id provenance and the no-search/when-to-use guidance, an agent has everything needed to invoke this 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 description coverage is 100% and the single 'id' parameter is fully documented there, including the same 'not a title and not a keyword' warning. The description repeats that constraint rather than adding new syntax or format detail, 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 precise verb+resource+scope: return the full public record of ONE asset looked up by exact id, and enumerates what the record contains (category, industry, tags, tech stack, demo url, price, editable source). This is clearly distinguishable from the search/filter siblings.

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?

Explicitly names the prerequisite (an id already obtained from search_3d_web_assets or recommend_3d_web_stack), states what the tool does NOT do (no keywords, no search), and routes the agent to search_3d_web_assets to get an id first. This is textbook when/when-not/alternative 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered. The description nonetheless adds non-annotation context: 'no authentication' and 'returns public metadata', which tell the agent about access requirements and data sensitivity.

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 short sentences, front-loaded with the return scope, then the exclusions/alternatives, then the safety and return characteristics. No sentence is 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 zero-parameter, read-only info tool with an output schema (which covers return values), the description supplies everything needed: what it returns, what it does not do, and which siblings to use instead.

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 tool takes zero parameters, so the baseline is 4. There is nothing for the description to clarify beyond what the empty schema already conveys, and it correctly does not invent parameter-like detail.

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 ('Return AETumi commercial pricing') plus the scope ('the four lifetime buy-once plans, what each includes and who it suits'). It explicitly distinguishes itself from the sibling asset tools, 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?

Gives explicit when-not guidance with named alternatives: 'Pricing only — it neither lists nor searches assets. For assets use search_3d_web_assets; for a single asset price use get_3d_web_asset.' The condition selecting each sibling is stated, not implied.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real context beyond them: it returns counts and names only, never the assets themselves, requires no authentication, has no side effects, and exposes only public metadata. It does not discuss ordering or potential result size, so it stops short of 5.

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?

Front-loaded with the core purpose and the enumeration-vs-retrieval split in the first two clauses, and the read-only/no-auth line is a compact trailer. Slightly dense — the enumeration of asset types (hero sections, shader/WebGL backgrounds, etc.) is illustrative padding, but it is short and scannable.

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?

An output schema exists, yet the description still usefully frames what the taxonomy contains and what it excludes. Combined with annotations covering safety and an empty input schema, an agent has everything needed 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?

Zero parameters with 100% schema coverage, so the baseline is 4. There is no argument syntax for the description to clarify; it correctly omits any parameter discussion.

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+resource (return the taxonomy of the AETumi commercial catalog: categories and industries with asset counts) and explicitly names the sibling it is not (search_3d_web_assets). An agent can distinguish it from filter_* and search_* siblings without inspecting any 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?

Gives an explicit when-to-use ('Call this to learn which filter values exist before searching') and a when-not/alternative ('to retrieve the assets use search_3d_web_assets'). The routing between enumeration and retrieval is fully specified.

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 readOnly, idempotent and non-destructive, so the safety profile is largely covered; the description's 'Read-only, no side effects' is partly redundant. It does add non-annotation context — 'no authentication' and 'returns public metadata' — which meaningfully informs invocation. Minor overlap keeps it from a 5.

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?

Front-loads the purpose, then the when-to-use routing, then the behavioral traits — a sensible order. The single dense sentence with em-dashes is a bit long, but every clause (plan contents, alternatives, auth/side-effect status) contributes.

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?

Output schema exists, so return values need not be explained, and the description still summarizes what the plan delivers. With annotations covering safety, 100% schema coverage, and clear sibling routing, nothing an agent needs to invoke this 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 coverage is 100% with per-parameter descriptions and an enum for framework, so the schema already carries the semantics. The description adds only indirect framing ('a described project') and does not clarify the optional industry/framework parameters beyond what the schema states. 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?

States a specific verb and deliverable ('return an OPINIONATED BUILD PLAN') and spells out the plan's contents (catalog assets, Three.js/WebGL architecture, framework choice, performance guidance). It explicitly distinguishes itself from search_3d_web_assets and list_3d_web_categories, so an agent can route correctly 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?

Gives an explicit trigger ('when the user describes something to BUILD rather than an item to look up') and names two alternatives with the conditions that select them: search_3d_web_assets for a plain ranked list, list_3d_web_categories for the taxonomy alone. Nothing is left to inference.

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, idempotentHint, destructiveHint=false, so the safety profile is covered; the description adds authentication context ('no authentication') and result-shape detail (paged list with id, title, category, industry, price, demo url, total, cursor). This goes beyond what annotations provide, though 'read-only, no side effects' partially restates the hints.

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?

Content-rich and front-loaded: purpose, when-to-use, exclusion, follow-up, and behavior in a compact block. Minor redundancy in restating read-only/no-side-effects alongside the annotations, but no sentence 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?

For a zero-required-param search tool with a rich schema and an output schema, the description covers everything an agent needs: scope, alternatives, follow-up, filters implied by the query field, and behavioral profile. Nothing material 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% and an output schema exists, so parameters and returns are already documented structurally. The description adds no syntax or format detail beyond what the schema carries (e.g. it never explains cursor usage or limit ranges), 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 and resource — searching the AETumi COMMERCIAL CATALOG of licensable 3D web assets — and enumerates the asset types covered. It explicitly distinguishes itself from find_experiences (Labs reference experiences, not for sale), so an agent can route correctly 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?

Gives an explicit when: user wants something to 'BUY, LICENSE AND SHIP'. Gives an explicit when-not with the alternative named: do not use for Labs reference experiences, use find_experiences instead. Also names the natural follow-up tool (get_3d_web_asset) for expanding a result.

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