DiffBeam Gaussian Beam Optics

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds the 'fast' and 'stateless' characteristics and prescribes the exact action to take on a changed result, which is behavioral context beyond the annotations. It does not contradict any annotation.

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 two sentences plus a conditional clause, front-loaded with the core purpose. Every sentence earns its place: the first states what it does, the second gives the actionable follow-up, and the third reassures safety. No waste.

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 stateless, read-only state-check tool with an output schema (present per context signals), the description covers everything an agent needs: what it checks, what to do when changed, and that it is safe and fast. There is no missing information that would prevent correct invocation or handling.

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% – each parameter ('known_server_revision', 'known_catalog_revision', 'known_tool_schema_revision') already has a clear description in the schema ('Previously observed...'). The description does not add any parameter-specific meaning beyond that, so it sits at the baseline of 3 for high schema coverage.

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 opens with a clear verb and resource: 'Check whether DiffBeam protocol, tools, or catalog data changed.' This precisely states the tool's function and inherently distinguishes it from the sibling search tools (search_fiber_collimators, etc.), which are for retrieving records, not checking state.

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 explicitly instructs the agent on when and how to use the result: 'If `changed` is true, refresh tool schemas and repeat any catalog searches before citing part numbers.' This is direct usage guidance that ties the tool to a specific workflow, and it notes the tool is 'read-only, fast, and stateless,' implying it is cheap to call and safe to use liberally.

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 mark it readOnly, idempotent, and non-destructive; the description adds that it only searches public catalog rows and 'only returns catalog matches', making clear this is a data lookup rather than a computation tool. This is meaningful behavioral context beyond the annotations, though it doesn't detail pagination or exact-match behavior.

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 a front-loaded one-line purpose, an explicit use-when list, and a clear exclusion. No filler; every sentence 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?

Given the full parameter documentation, output schema, and safe annotations, the description covers scope, result content, and the key misuse case. It doesn't explicitly distinguish itself from search_fibers/search_lenses within the text, but the domain-specific resource and fields make that distinction inferable.

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 already documents all four parameters, so the baseline is 3; the description raises this by explaining the intended query style (part number or short component phrase, vendor-neutral terms unless vendor/family named) and lists catalog attributes that map to search terms. It adds meaning without repeating schema details.

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?

Opens with a specific verb and resource — 'Search public fiber-collimator catalog rows' — and enumerates the real-world attributes it returns (part numbers, EFL, coating range, connector type, clear aperture). This clearly distinguishes it from the sibling lens/fiber search tools and generic optical calculators.

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 trigger conditions ('Use when the user asks for real collimator/coupler part numbers, links, EFL, coating range, connector type, clear aperture, or vendor data') and an explicit exclusion ('Do not use as a generic Gaussian-beam solver'). It does not name a specific sibling alternative for the excluded case, so it falls just short of fully explicit alternative 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?

With readOnlyHint and idempotentHint already present, the description adds non-obvious behavior: it 'never reads or writes planner workspaces', only returns catalog data and public URLs, and offers a specific retry policy for transient transport errors. This goes beyond the annotations and helps an agent reason about safety and repeatability, even if it doesn't mention rate limits or authentication.

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 only a few sentences but carries purpose, usage context, behavioral constraints, and retry handling. There is no redundancy or filler, and the most important statement ('Search public fiber catalog rows') is 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 simple read-only search tool with a rich input schema and an output schema present, the description covers the core usage, behavioral scope, and retry procedures. It could elaborate on result set handling or when not to use it, but those are not critical gaps given the structured schema and the search-based context.

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 already documents all three parameters (coverage 100%), so the baseline is 3. The description enriches the query intent by naming fiber attributes and the wavelength use case, but it does not add concrete parameter-level details beyond the schema. It relies on the schema's own parameter descriptions, which are already good.

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's purpose with a specific verb+resource: 'Search public fiber catalog rows'. It enumerates the fiber attributes it is appropriate for (part numbers, mode-field diameter, numerical aperture, wavelength compatibility), which mainly distinguishes it from lens/collimator tools. However, it does not explicitly mention or contrast with sibling tools, so cross-tool differentiation is left to inference.

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 says 'Use when the user asks for ...', which is direct and explicit. But it lacks an explicit 'don't use when' section and does not point the agent to one of the siblings like search_fiber_collimators or search_lenses. The retry guidance is useful, though it's about invocation behavior rather than alternative selection.

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 description doesn't need to repeat safety traits. The description adds valuable behavioral guidance: 'Return matches as evidence; never claim a part exists unless it appears in the result.' This is a critical anti-hallucination constraint that goes beyond annotations. It effectively communicates the tool is a read-only search and sets expectations for evidence-based responses.

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 crisp sentences with zero fluff. The core verb and resource are front-loaded in the first sentence, the usage trigger is the second, and the evidence constraint is the third. Every sentence earns its place, and the structure is highly scannable for an agent.

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 has an output schema, so return-value explanation is unnecessary. The description covers purpose, usage triggers, and a critical behavioral constraint. The mention of 'public lens catalog' implies accessibility without special permissions. Given that siblings are clearly differentiated by resource type and the annotations carry safety information, the description is complete for an agent to call this 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%, meaning every parameter (query, limit, diameter_mm, wavelength_nm, focal_length_mm) has a description. The tool description does not add any parameter-specific guidance beyond the schema; it only refers to query being used for 'real lens part numbers' etc., which is already covered in the schema's query description. Baseline for high coverage is 3, and the description does not compensate with extra semantics, so 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?

The description states a specific verb and resource: 'Search public lens catalog rows.' It also enumerates the user intents it serves (part numbers, links, focal lengths, diameters, coatings, purchasable candidates), and the resource name 'lens' clearly differentiates it from the fiber-focused siblings (search_fiber_collimators, search_fibers). No ambiguity about what it does or how it differs.

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 says 'Use when the user asks for...' and lists the conditions, providing clear context for when to invoke the tool. It lacks explicit exclusions or mention of alternatives (e.g., 'use search_fiber_collimators for collimators'), but the sibling names themselves are self-explanatory and the usage context is unambiguous. A clear usage trigger without an explicit negative or alternative earns a 4.

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