KerfScript

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: paginated long guides and the nextOffset continuation signal, which an agent would not otherwise know. Missing: what a doc entry looks like and whether topic names are case-sensitive.

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, zero filler, with the core purpose front-loaded and the discovery and pagination hints following in priority order.

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, yet the description still discloses the listing mode and the pagination contract, which is the minimum an agent needs to drive a two-param reader. A brief note on valid topic identifiers would close the remaining gap.

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 0%, so the description must carry the burden. It explains both params at a functional level (omit topic to list; offset pages through long guides), but leaves the format of `topic` undefined and never reconciles the `offset` parameter name with the returned `nextOffset` value, which invites a mis-call.

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: reads KerfScript language and JavaScript integration documentation for building laser-cutting generators. Clear what the tool returns (docs) versus the sibling names kerfscript_examples/parameters/render, though it never explicitly contrasts itself with kerfscript_examples, which is the closest overlap.

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?

"Omit topic to list guides" gives a concrete entry pattern and is genuinely useful for discovery. But there is no guidance on when to prefer this over kerfscript_examples or kerfscript_parameters, and no statement of preconditions or typical call flow.

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, closed-world, non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: what fields are searched and that the id mode returns .kerf source rather than a listing. It omits pagination behavior despite the offset parameter.

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 waste, with the primary search mode front-loaded and the secondary id-to-source mode stated second.

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 and zero schema description coverage, the description should explain result shape and paging. It conveys the two-step retrieval model but leaves offset and the form of the results list unspecified.

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 0%, so the description must carry the load. It explains id (must come from prior results) and query (matches title/id/tags), but the offset parameter and its paging semantics are never mentioned in either schema or description.

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 ("Find ... examples") plus the searchable fields (title, id, tags) and a second mode (id → .kerf source). That is far more than a restatement of the name, though it never explicitly distinguishes itself from kerfscript_docs or kerfscript_render.

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 two-step flow is implied: search first, then supply an id from the results to retrieve source. However, there is no guidance on when to prefer kerfscript_docs or kerfscript_parameters over this tool, and no statement of when this tool is not appropriate.

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 closed-world, so the safety profile is covered. The description adds genuinely useful behavior — it parses statically without performing geometry rendering, i.e. it is a cheap analysis pass — but says nothing about failure modes for invalid .kerf source or the shape of what comes back.

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, the extraction target is front-loaded, and the non-rendering caveat follows immediately. 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 should say something about what the extracted settings/ranges look like, and it only names them in the abstract. Combined with the unresolved `source` semantics and no error behavior, a read-only one-param tool is left with a couple of 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?

There is a single parameter, `source`, with 0% schema description coverage (only type and maxLength 64000). The description mentions ".kerf source" but never clarifies whether `source` is the raw .kerf code text or a file path/reference — the one ambiguity an agent must resolve to call this correctly.

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?

"Extract editable settings and customizer ranges from .kerf source" is a specific verb+resource with a stated downstream purpose (build a generator UI). "Parses without rendering geometry" implicitly carves it out from kerfscript_render, though the other siblings (docs, examples) are not addressed.

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 phrase "to build a generator UI" implies the use case, and "without rendering geometry" hints at when to prefer this over kerfscript_render. There is no explicit when-to-use/when-not-to-use statement or named alternative.

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/closed-world, but the description adds genuinely new behaviour: pure in-memory evaluation with no filesystem or network imports, fixed millimetre units, a bundled Atkinson font, and hard limits of 100 parts and 10 sheets. What it omits is how the rendered files are returned and what warnings/errors look like.

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?

Four short sentences, front-loaded with what is produced, then constraints, then the escalation path. No filler and no repetition of schema or annotation content.

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 carries the return-value burden and only partly discharges it: it says output is one file per sheet with part sizes, layers and warnings, but not the response shape (inline SVG/DXF text vs. references) or error/warning reporting. For a 9-parameter render tool that is a meaningful remaining gap.

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 only 22% across 9 parameters, so the description needs to compensate. It clarifies units for the numeric geometry inputs ("Uses millimetres") and that libraries are virtual rather than fetched, but says nothing about gap, kerf, margin, layout or params, leaving most parameters undocumented in both places.

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 ("Render .kerf source") plus concrete outputs (SVG or DXF, one file per sheet) and included metadata (part sizes, layers, warnings). It is clearly distinguishable from the docs/examples/parameters siblings, though it never names them 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?

"For production generators install @mylasertools/kerfscript locally" gives one real routing signal, and the 100-part/10-sheet bound tells the agent when the tool will refuse work. However there is no explicit statement of when to pick this over kerfscript_docs, kerfscript_examples or kerfscript_parameters, so the usage guidance is implied rather than stated.

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