Nifra docs

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

The readOnlyHint=true annotation already covers the safety profile. The description adds that it returns 'ONLY the matching sections' and returns 'top matching sections' (scoping the result set), plus the cheap-index behavior. This adds meaningful context beyond the annotation but doesn't describe pagination or the exact return shape, which is acceptable given no output schema.

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, all earning their place: purpose, dual usage modes, and sibling distinction. Front-loaded with the purpose verb. Zero 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 search tool with only 2 parameters (both fully documented in schema), readOnlyHint=true annotation, and no output schema, the description fully covers what the agent needs: how to invoke (with/without query), what to expect back (matching sections), and when to delegate to nifra_types. Complete.

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 both parameters (limit and query) are already documented in the schema. The description adds the example query 'isr revalidate' and the omission-of-query-for-index behavior, plus that limit controls 'Max sections.' This is baseline-plus value, but the schema already carries the semantic weight.

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 verb (search), resource (nifra's framework documentation), and scope (returns ONLY matching sections, covering auth, uploads, ISR, WebSockets, loaders, deployment). It distinguishes itself from nifra_types sibling by explicitly naming the alternative for exact TypeScript lookups.

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?

Provides explicit when-to-use guidance: call with no query for the section index, pass a query for top matching sections. It also names an explicit alternative (nifra_types for exact TypeScript) and tells the agent to avoid reading llms-full.txt (~150 KB). This is strong when/when-not 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?

The description adds the verified/typechecked behavior ("Every snippet is typechecked against the installed nifra version") and the return format ("Returns code as TEXT for direct use"), which complements the readOnlyHint=true annotation. It doesn't fully detail pagination or grouping behavior, but the annotations cover the read-only safety profile. Solid transparency above the annotation baseline.

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 dense but efficient, front-loading the core purpose in the first sentence and covering usage, alternatives, return format, and query semantics in a compact paragraph. Every sentence earns its place with 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?

For a text-returning search tool with no output schema and full param coverage, the description adequately covers what's returned (code as TEXT), how to use it (with/without query), and when to prefer it (verified vs from-memory). Slightly more on the grouped index structure could help, but this is largely complete for its complexity.

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 (limit, query) are documented in the schema. The description adds example query values ("protected route", "upload", "isr revalidate") and clarifies the omit-query-for-index behavior, which is marginal value over the schema but not substantial. 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?

The description uses a specific verb+resource ("Get a VERIFIED, copy-pasteable nifra code example") and lists concrete task categories (auth route, file upload, ISR page, etc.). It clearly distinguishes from siblings by naming nifra_gallery as the visual alternative and emphasizing this tool returns text for direct use.

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 "PREFER THIS over writing nifra code from memory (training data drifts)", giving strong when-to-use guidance. It also names the alternative nifra_gallery for visual browsing and explains the call-with-no-query vs pass-query distinction. This is exemplary usage 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, and the description title also states 'Browse'. The description adds behavioral context beyond annotations: it's an interactive widget (not a data-returning API), opens a gallery, filters client-side, and pre-filters server-side. It doesn't describe navigation or exit behavior, but the interactive-widget nature is usefully disclosed.

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, zero waste. Front-loaded with the primary purpose, then the exclusion/alternative, then the parameter nuance. Every sentence earns its place and the whole thing is readable at a glance.

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 single-optional-param read-only browsing widget with 100% schema coverage and clear annotations, this description is complete. It tells the agent what the tool does, when to use it instead (vs nifra_example), and how the param behaves. No output schema needed since it's a widget launch, not a data return.

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 the query parameter. The description adds value beyond the schema by explaining that query pre-filters server-side AND that the widget also filters client-side — clarifying the dual filtering behavior. It also clarifies query is optional (0 required params).

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: 'Open an interactive, filterable gallery of ALL of nifra's verified code examples (MCP Apps widget)'. This clearly distinguishes it from sibling nifra_example by explicitly stating what it is NOT for and where to go instead. The scope ('ALL'), format (gallery/widget), and use-case (browsing/discovering) are all specified.

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 guidance provided: 'NOT for fetching one snippet as text: use nifra_example for that.' This names the sibling alternative directly and states when NOT to use this tool. Additionally, it explains the query parameter behavior (pre-filter + client-side filtering), giving the agent clear usage context.

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?

Description explains what each step provides (goal, how to do it including which tool emits the correct artifact, and how to verify it), and that each step composes the other nifra_* tools. Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with these. Adds compositional context beyond annotations without contradicting 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-structured single paragraph that front-loads the core purpose, then explains invocation modes and usage context. Every sentence adds value: the ordered sequence, the contrast with siblings, the no-args vs step:N behavior, and when to use. No wasted words.

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 1-param tool with 100% schema coverage, readOnly annotations, and no output schema, the description is thorough: it names the full sequence, defines what each return contains, and situates the tool among siblings. Minor gap: it doesn't clarify whether the step sequence is reusable across multiple sessions or tied to a current project state, but overall this is well-specified for its complexity.

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 step parameter is fully documented in the schema. The description adds significant semantics beyond the schema by explaining the 1-based indexing behavior, that omitting it returns the index, and that passing a step number expands its goal/how/verify. Rich functional meaning added beyond the bare 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?

Description clearly states this is a guided ordered path for building a nifra app end to end, with an explicit sequence (create → page route → loader → typed API → typed client → auth → background jobs → deploy). It explicitly distinguishes this from the random-access search of nifra_docs/nifra_example, which differentiates it from 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?

Provides explicit when-to-use guidance: 'Use it when scaffolding a new app or learning nifra's flow'. Also distinguishes from siblings by contrasting ordered guided path vs random-access search of nifra_docs/nifra_example. The description explains how to invoke it (no args for index, step: N for details) and what each call returns.

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, so no contradiction there. The description adds valuable behavioral detail: that `name` lookups return complete declarations, query results collapse oversized bodies, and that a single match can be tens of thousands of characters. It clearly discloses the return shape and format without contradicting 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?

The description is dense but every sentence earns its place - it packs purpose, mode selection, format guarantees, and an anti-path (don't read node_modules) into a tight block. Front-loaded with the core promise before diving into mode details. Zero 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 read-only lookup tool with no output schema, 100% covered params, and zero required parameters, this description is fully complete. It explains return formats for each mode, size/performance caveats, defaults, and boundary behaviors - nothing is left ambiguous for someone looking up type declarations.

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 descriptions are already detailed, so baseline is 3. The description adds meaningful context beyond schema: the relationship between name/query/full modes, the collapse behavior, and the default limit semantics. This elevates it above the baseline, though the schema already handles most of 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?

The verb 'Get' plus explicit resource (TypeScript declarations of @nifrajs/* symbols) makes the purpose unmistakable, naming the exact kind of output (interface, type, class, function, const). It clearly distinguishes from siblings by emphasizing this is 'THE SOURCE OF TRUTH' for types vs docs/examples/learn, and even names what NOT to do (read node_modules .d.ts).

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?

Provides explicit when-to-use instruction ('do NOT read node_modules...call this instead'), clear mode distinctions (name for exact, query for search, omit both for index), and when to override with full:true. This is exemplary guidance on invocation decisions.

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