Nifra docs

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the no-query call is 'cheap' and returns a section index, results are limited to matching sections only, and the ~150 KB cost of the alternative is quantified. It stops short of noting rate limits or result truncation, so not 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?

Four tight sentences, front-loaded with the core action and scope, then the two invocation modes, then the cost rationale and the alternative tool. Every sentence carries routing or behavioral information with 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?

No output schema exists, but the description characterizes the return shape (matching sections only vs. a section index) and names the sibling tools that cover the remaining needs. For a two-parameter read-only search tool, an agent has everything required 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?

Schema coverage is 100%, so both parameters (limit default 3/max 5, query maxLength 256) are already documented — baseline 3. The description still adds value: a concrete query example ('isr revalidate') and the semantic consequence of omitting query for a cheap index, which clarifies intent rather than restating types.

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 (nifra's framework documentation) with explicit scope: returns ONLY matching sections, with a no-query index mode. It explicitly distinguishes itself from sibling nifra_types (exact TypeScript) and from reading llms-full.txt, so an agent can route 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 for both invocation modes (no query = cheap index; query = top matching sections) and names the alternatives not to use: nifra_types for exact TS, and llms-full.txt as the expensive path. Nothing about selection 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 cover read-only, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description adds genuine value beyond that: snippets are typechecked against the installed Nifra version so they compile as-is, and results are returned as plain text code.

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, front-loaded with the value proposition (verified, copy-pasteable, compiles as-is), followed by the return format and then invocation instructions. No filler, though the long category list is close to padding.

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 states the return format (code as text for direct use). Annotations cover the safety profile and the schema is fully documented, leaving little missing for a simple two-parameter lookup 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 description coverage is 100%, so both parameters (query, limit) are already documented including the default/max on limit. The description largely restates the schema's omit-for-index behavior and adds only example query phrases, so 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: get a verified, copy-pasteable code example for a named task, and enumerates the covered categories (auth route, file upload, ISR page, loader/action, typed client, SSE, deployment). It never distinguishes itself from the close siblings nifra_docs, nifra_learn, or nifra_types, so an agent must infer the boundary.

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 clear invocation guidance (no query = grouped index, query = matching snippets) with concrete query examples like "protected route" and "upload". However it offers no when-to-use versus alternatives guidance, which matters given the overlapping nifra_docs and nifra_learn siblings.

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, non-destructive, and closed-world, so the safety profile is covered. The description adds non-obvious behaviour beyond that: it returns "the likely cause, a concrete fix, and how to verify it," and defines the no-args index mode.

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 front-loaded sentences that each carry information: purpose, return shape, topical coverage, and invocation. The topical enumeration is slightly list-like, but it helps the agent judge relevance, so it earns its length.

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?

There is no output schema, and the description compensates by summarising the return payload (cause, fix, verification). Combined with annotations covering the safety profile and an explicit no-args index mode, 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?

Schema description coverage is 100%, so the schema already documents every parameter (baseline 3). The description adds value by giving concrete example symptom values ("hydration mismatch", "value stopped updating") that illustrate free-text intent beyond the schema's generic wording.

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: "Diagnose a client-side Nifra problem by symptom across every adapter." This is clearly distinct from sibling tools (nifra_docs, nifra_example, nifra_gallery, nifra_learn, nifra_types), which are reference/learning surfaces rather than a symptom-driven diagnostic. An agent can route to it 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?

Explicitly tells the agent how to invoke: "Call with no args for the index; pass symptom and/or adapter to filter," which resolves the ambiguity of a 0-required-param tool. It does not, however, state when NOT to use it or name an alternative sibling for reference-style questions.

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 the safety profile is covered. The description adds non-obvious context beyond the annotations: it is an MCP Apps widget (interactive UI) and filtering happens both server-side via query and client-side, which affects how an agent should treat the result. It stops short of describing empty-result or auth behavior, but that is minor given 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?

Three tight sentences, front-loaded with the primary purpose, then the exclusion/alternative, then the parameter hint. No sentence is redundant.

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 a single optional parameter, the description supplies everything needed: what the tool returns (an interactive gallery widget), its scope (ALL verified examples), how filtering works, and when to prefer a sibling. Nothing critical 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% for the single parameter, so baseline is 3. The description adds meaning beyond the schema's 'Pre-filter examples by keyword': it clarifies that query is a pre-filter and that the widget additionally filters client-side, telling the agent the filter need not be exhaustive.

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 — opening an interactive, filterable gallery of nifra's verified code examples — and names the sibling (nifra_example) it is not. An agent can distinguish it from the other nifra_* tools 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?

Explicitly states the exclusion ('NOT for fetching one snippet as text') and routes to the correct alternative ('use nifra_example for that'). It also frames the intended use case: browsing and discovering what exists.

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, openWorldHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. Beyond that, the description discloses non-obvious behavior: no-arg calls return a step index, while step: N returns goal + method + verification, and each step composes other nifra_* tools. It doesn't mention any bounds on step count or error behavior for an out-of-range step.

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 ordered-sequence claim and the sibling differentiation are front-loaded in the first clause, and each subsequent sentence adds routing or call-shape information. It is dense, with the parenthetical step arrow-chain being somewhat heavy, 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?

There is no output schema, so the description must describe returns — and it does, covering both the no-arg index and the per-step payload (goal, how to do it, how to verify). For a single-optional-param, read-only tool, an agent has everything needed to call and interpret it.

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% for the single `step` parameter, so the baseline is 3. The description goes beyond the schema by defining the two distinct modes (omitted = index, provided = expanded step) and specifying exactly what content each yields, which is real semantic value the schema's 'expand' wording does not carry.

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 ('walk the guided path to build a nifra app') and immediately pins down its shape: an ORDERED sequence of named steps. It explicitly distinguishes itself from siblings by naming nifra_docs and nifra_example and characterizing them as 'random-access search', so the agent can pick the right tool without opening schemas.

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 ('scaffolding a new app or learning nifra's flow') and a clear when-not via the contrast with nifra_docs/nifra_example. The call patterns (no args vs step: N) are also spelled out, 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?

Goes well beyond the annotations: signatures are generated from the package's built .d.ts, a name lookup is always the complete declaration, a query returns a one-line summary plus signature with the body collapsed, and `full: true` overrides that. This discloses result-shaping behavior the readOnly/idempotent hints cannot convey.

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 parameter-mode guidance in one dense paragraph with no filler. Slightly long, but nearly every clause carries distinct information (index mode, collapsing, full override), so the size is largely earned.

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 still explains the three return shapes (index of names, full declaration, summarized-plus-signature) and how to expand them. An agent has everything needed to call it correctly and interpret the result.

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 adds interaction logic beyond the schema: name vs query vs omit semantics, and that `full` applies only in query mode and overrides the default collapsing. It meaningfully disambiguates how the parameters combine.

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 (Get) and resource (the exact TypeScript declaration of any exported @nifrajs/* symbol) and enumerates the symbol kinds covered. The phrase 'returns the complete declaration rather than prose' explicitly distinguishes it from prose-oriented siblings like nifra_docs, letting an agent choose 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 clear mode selection: pass `name` for an exact symbol, `query` to search by keyword, omit both for the per-package index. This covers when-to-use each mode well, though it doesn't name sibling alternatives (e.g. when to reach for nifra_docs instead), so no explicit exclusion guidance.

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