Laplace’s Mini World

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds the return shape (chapter ids/titles, lab setting ids, ranges, options), which is useful given there is no output schema, but it says nothing about pagination, auth, or 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 dense sentences with no filler, and the primary capability plus the payload are front-loaded. The trailing 'for show_model' clause is slightly compressed and takes a second read to parse, 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?

With no output schema, the description correctly carries the return-shape burden by naming chapter ids/titles and lab setting ids, ranges, and options, and it supplies routing context against siblings. Only operational details (pagination, ordering) are missing, which is minor for a simple list 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?

Schema coverage is 100% with only two parameters, so the schema already explains slug and the zh/en enum. The description's 'one plate' phrasing loosely reinforces that slug selects a single plate, but adds no format or constraint detail beyond 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 ('Lists one plate's chapters') plus the secondary payload (lab settings), and ties itself to show_model. The 'plate/chapter' vocabulary is domain-specific but consistent, so an agent can tell it apart from search_models and show_model.

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: use it when the user wants a different part of a plate than search_models returned, or wants to set the lab settings. It names the competing tool but does not state the inverse case (when to prefer search_models/show_model), so it stops short of full when/when-not routing.

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 cover the safety profile (readOnly, idempotent, closed-world), and the description adds search mechanics (two-pass: question index then titles/topics), result shape (slug, chapter, lab settings), and the no-results condition. It doesn't mention rate limits or latency, which is a minor gap.

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 usage trigger with concrete bilingual examples, then mechanics, then exclusions. Slightly long and example-heavy, but every sentence earns its place for a routing tool.

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 search entry point with full schema coverage and annotations, the description is complete: trigger conditions, search behavior, return contents, follow-up tool, and failure mode are all covered.

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 schema already documents query, lang, and limit thoroughly including enums, bounds, and defaults. The description restates query semantics (user's own words, any language) but adds little beyond the schema. 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 (search) and resource (interactive 3D models/plates on world.lapla.si), with the exact question types it covers and hand-off to show_model. Clearly differentiates from siblings list_chapters and show_model.

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 with example queries, explicit when-NOT-to-use (news, prices, homework calculations, medical/legal/financial advice), and names the follow-up tool show_model. Nothing 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 readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description adds genuinely useful non-obvious context: it renders an interactive UI in the conversation and emits a fallback text summary plus link for non-UI clients. Minor gap: it doesn't say what happens if the slug or chapter id is invalid.

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 what the tool does before the usage rule and the fallback behavior. The first sentence carries several clauses but each conveys distinct information. Slightly dense, 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?

No output schema exists, so the description must cover returns — and it does, stating it yields a short text summary and the plate's link. Combined with the read-only annotation profile and full schema coverage, 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 coverage is 100%, so every parameter including nested params and lab already has a description. The description reinforces provenance ('with the slug and chapter (and params) it returned'), but adds no syntax or format detail beyond the schema. 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 resource ('Shows one interactive 3D model from world.lapla.si') plus its interaction model (turn, step through chapters, try the lab). It is clearly distinguishable from siblings search_models and list_chapters, which it explicitly positions itself after.

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 trigger conditions: 'Use it after search_models with the slug and chapter (and params) it returned, or when the user names a plate.' This names both the upstream dependency and an independent trigger, 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.