ProjectThunder

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context by disclosing that every result point carries a source URL and that it returns version notes and implementation partners, which goes beyond the annotation metadata.

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 a single dense sentence that front-loads the purpose and includes a useful examples sentence. It is not overly verbose and every clause contributes to understanding the tool's scope, though a slight structural split could improve skimmability.

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 an output schema present and annotations covering safety, the description is largely complete for a read-only assessment tool. It explains inputs, output composition, and source attribution; minor ambiguity around 'what to settle first' is acceptable given the output schema likely details the returned structure.

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 baseline is 3. The description adds value beyond the schema by showing combined ERP+version example inputs like 'Dynamics GP 2018' and 'NAV 2009 R2', which clarifies expected formatting for the erp and version parameters beyond the schema's separate examples.

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 specific verb and resource: for an ERP (and optionally version/platform), it returns integration fit details. It lists concrete outputs (integrates with Sana/BigCommerce/DynamicWeb/Wardenclyffe, version notes, priorities, guides, partners, source URLs), which clearly distinguishes it from sibling tools like get_erp_partner or search_site.

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 clear context about when to use the tool (when assessing ERP fit with an e-commerce platform) and even provides example inputs. It does not explicitly name alternatives or state when not to use it, but the scope is clear enough for an agent to route correctly.

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, so the description does not need to restate safety. It adds valuable behavioral context about language handling, including which domains correspond to each language and that the ERP partner directory is English-only, requiring calls without a language parameter. This goes beyond the annotations and helps the agent understand side effects and constraints.

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 with zero waste. The first sentence front-loads the main content, and the second provides usage guidance. Every word earns its place, making it both concise and effective.

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 is simple (one optional parameter, no required fields), has an output schema, and the description fully explains what the tool returns and the language behavior. An agent can confidently call it without ambiguity. The description is complete for this tool's complexity and leaves no critical 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?

The schema already describes the language parameter with 100% coverage, so the baseline is 3. The description adds extra nuance about which specific domains serve each language and the English-only restriction for partner data, which is not in the schema. This enriches the semantics and helps the agent make informed choices about parameter values.

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 explicitly lists the specific data items (phone, email, contact page, mailing address, team location, and contact form topics) and the title clarifies the purpose. It is clearly distinguishable from siblings like get_page or list_pages because it focuses on contact information. However, it lacks an explicit verb like 'retrieves' or 'gets,' though the intent is unmistakable.

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 provides a clear when-to-use condition: 'Use it when someone wants to talk to ProjectThunder about a project.' It does not explicitly name alternatives or exclusions, but the sibling list includes tools like get_page and list_pages, and the description's specificity makes it obvious this is the contact tool. This is adequate guidance without being overly verbose.

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 and idempotentHint, covering safety. The description adds the detail that lookup is by slug or name and returns a single listing, which is mild extra context. It does not mention error behavior or return format, but the output schema exists. No contradiction with 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 a single sentence that front-loads the action and includes a concrete example. Every word contributes value, with no redundancy.

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 presence of an output schema, annotations covering safety, and a fully documented input parameter, the description is sufficiently complete for a simple getter. It gives the source for slugs (list_erp_partners), which is helpful. Missing explicit not-found behavior, but unlikely to hinder correct invocation.

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% – the parameter is fully described as 'The partner's slug (from list_erp_partners) or its name.' The description adds an example but no new semantic meaning 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?

The description states a specific verb ('Returns'), a clear resource ('one listing from the ERP partner directory'), and the lookup method ('by slug or name'), with an illustrative example. This clearly distinguishes it from sibling tools like list_erp_partners, which presumably returns multiple listings.

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 implies usage (single partner lookup by slug/name) but does not explicitly contrast with alternatives or state when not to use it. Sibling tools like list_erp_partners are not mentioned, so guidance is only implicit.

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 idempotentHint=true. The description adds useful behavioral context: it accepts full URLs or paths, handles multilingual domains (projectthunder.mx, pt.projectthunder.com, projectthunder.asia), and notes that the ERP partner directory exists only in English. It also explains language override behavior. No contradictions with 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?

Three concise, front-loaded sentences. The first sentence states the core function and output; the second covers input formats; the third explains language behavior. No redundancy or 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?

Given no output schema, the description fully explains what is returned (Markdown with title, URL, summary, full content). It also covers input variations and language behavior, including the edge case of ERP partner content being English-only. No critical information is missing for an agent 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 both url and language are documented. The description adds value by explaining how the URL host implies a language and how the language parameter overrides that. This clarifies the interaction between parameters, going beyond schema descriptions.

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 action ('Returns one page or Insights article'), the resource (projectthunder.com pages), and the output format (Markdown with title, URL, summary, full content). It clearly distinguishes itself from listing and search siblings by focusing on retrieving a single page's full content.

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 implies usage for fetching a specific page's full content, contrasting with listing tools like list_pages and list_articles, and search_site for discovery. However, it does not explicitly state when not to use it or name alternatives; the context is clear but not explicit.

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, and non-destructive behavior, so the bar is lower. The description adds useful behavioral context beyond annotations: the result is ordered newest first, includes publish dates and summaries, and content varies by language site. This exceeds the annotation baseline without contradicting it.

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 carry the core behavior, ordering, topics, reading follow-up, and language condition. Every clause earns its place, and the most important scoping information 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?

Given a single optional parameter, a detailed schema, and an output schema, the description provides everything an agent needs to call the tool correctly: scope, ordering, content shape, language behavior, and a pointer to get_page for reading a full article.

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%, and the language parameter is already documented in detail including defaults and site mapping. The description adds a brief mention of language but does not materially go beyond the schema, so the baseline of 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: lists Insights articles, enumerates the topic areas, and specifies that results include publish dates and summaries ordered newest first. This clearly distinguishes it from siblings like list_case_studies, list_erp_partners, get_page, and search_site.

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 routes follow-up reading to get_page and gives a conditional usage rule for language selection (English default; set language for Spanish, Portuguese, or Chinese). It does not state exclusions relative to list_case_studies or list_erp_partners, but those distinctions are reasonably inferable from the tool names and the clear article scope.

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 safety profile is covered. The description adds useful behavioral context about the returned fields and optional filtering, but it does not disclose ordering, pagination, or result limits. This is acceptable given the annotations but not exceptional.

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 concise sentences with no filler. It front-loads the core content of the tool and then states the filtering options. Every phrase contributes useful 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 simple read-only list tool with an output schema, the description covers the returned content and the two optional filters. It is complete enough for an agent to call correctly. A small gap is the lack of any guidance about sibling tools, but this is not critical given the clarity of the resource.

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 both parameters well. The description restates that filtering is optional by platform or keyword but adds no new semantic 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?

The description clearly states the resource: ProjectThunder portfolio case studies, and enumerates the fields returned (client, platform, industry, ERP, what was built). It is distinct from sibling tools like list_articles and list_pages because it focuses specifically on case studies, though it does not explicitly name a sibling.

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 implies when to use the tool: to list portfolio case studies, optionally filtered by platform or keyword. However, it does not explicitly state when to prefer this over alternatives such as list_articles or search_site, nor does it mention any exclusions or prerequisites.

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, so the safety profile is covered. The description adds the optional filter and the listing fields, but does not disclose behavior like pagination or result limits; the output schema likely covers return details.

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 compact sentences: the first states the core behavior with a front-loaded verb, and the second summarizes the listing contents. There is no fluff or redundant explanation.

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 list tool with one optional parameter, this description is complete enough. Annotations and the output schema cover safety and return structure, while the description supplies what the tool returns and how to filter.

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%, and the erp parameter already documents name-or-slug usage with examples. The description's ERP examples largely repeat the schema, adding little beyond the baseline.

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 specific verb and resource: "Lists the firms and independent consultants in ProjectThunder's ERP partner directory" and adds the optional ERP filter. This clearly distinguishes it from article/page lister siblings and from the singular get_erp_partner.

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 context is clear: use this tool to list directory partners, optionally filtered by ERP. It does not explicitly name when-not to use it or point to alternatives like get_erp_partner for a single partner, so it stops just short of full 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 this read-only, idempotent, and non-destructive. The description adds useful behavioral context beyond annotations, including site ordering and the fact that English is the default with Spanish, Portuguese, and Chinese results coming from separate sites.

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 with no filler. The purpose, output fields, ordering, and language behavior are all front-loaded, and 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 output schema, full parameter coverage, and annotations declaring safety properties, the description provides everything needed to invoke the tool correctly. Nothing essential 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 description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds little beyond restating that English is default and that setting language targets other sites, which is already present in 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?

The description clearly states the verb ('Lists'), the resource ('pages on projectthunder.com'), and the output fields ('title, URL, type and one-line summary'). It is distinguishable from specialized siblings like list_articles or list_erp_partners, though it does not explicitly name them.

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 says what the tool does but gives no guidance on when to choose it over alternatives such as search_site, list_articles, or list_erp_partners. There are no exclusions or comparisons to sibling tools, leaving tool selection up 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 the operation read-only, idempotent, and non-destructive, and the description does not contradict them. It adds useful context that the plan is based on ProjectThunder's published method and that points link to source pages, but it does not disclose any additional behavioral traits beyond that.

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 content is dense and relevant, with the main purpose front-loaded in the first clause. However, the opening sentence is a long run-on that packs many list items together, making it harder to parse than necessary.

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 rich annotations, 100% schema coverage, and an existing output schema, the description covers the plan's scope, source method, and linked provenance. No critical invocation details are missing, though usage guidance versus sibling tools is absent.

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 'from', 'to', and 'erp' clearly. The description reinforces the migration-around-ERP context but adds no per-parameter format, constraints, or examples beyond what the schema provides.

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 deliverable ('A rollout plan for moving a B2B store from one platform to another around an ERP') and enumerates what the plan contains, so the purpose is unambiguous. It does not explicitly contrast itself with sibling tools like assess_erp_commerce_fit, but the resource and content list make it distinct.

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 intended use is implied by the migration context and the plan contents, but there is no explicit when-to-use guidance or mention of alternatives. An agent is left to infer that this is the right tool for migration planning rather than, say, evaluating ERP fit.

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 supply idempotentHint, and the description explains the exact cache behavior (one fresh scan per 30 days, saved scan with date returned on repeat). It also discloses latency (10–40 seconds) and the no-account/free aspect, all beyond the structured fields.

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 front-loaded with the core action and then details output, caching, and timing. It is slightly long due to enumerating every report category, but each sentence adds operational or output context.

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 an output schema present and a single well-documented parameter, the description covers everything an agent needs: what is returned, how long it takes, repeat-call behavior, and no auth. Nothing material 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 description coverage is 100%, and the url parameter is already documented with format examples. The description adds only the 'public' constraint and home-page scope, so it stays at the baseline.

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 ('Scans'), a specific resource ('one public website'), and a concrete outcome (platform/technology detection plus a summary and scores). This clearly differentiates it from siblings like get_page or search_site, which are navigation/content tools, without needing to name them.

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 clear operational context: only public home pages are scanned, scans are cached for 30 days, and repeats return the saved scan. It does not explicitly say when to prefer this over sibling tools, but the constraints make its scope evident.

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 discloses behavioral traits beyond the annotations: results are 'best matches with a snippet' (so full content is not returned), language changes which site is searched, and the get_page pointer implies snippets are truncated. Annotations already cover read-only/idempotence, so these additions are meaningful context rather than repetition.

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 no filler, and the core purpose is front-loaded. The enumeration of content types is long but useful for an agent deciding whether search_site covers a given topic. It earns its place, though the list could arguably be condensed.

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 a 100%-described schema, an output schema, and annotations covering the safety profile, the description is complete: it covers what the tool searches, the shape of results, language behavior, and how to proceed with a full result via get_page. Nothing an agent needs to call this tool correctly 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 description coverage is 100%, so the input schema already documents query, type, limit, and language. The tool description adds no parameter-level meaning beyond reinforcing the language behavior and content scope. This aligns with the baseline 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 starts with an explicit verb+resource, 'Search the pages on projectthunder.com', and enumerates the exact content types covered (services, platform guides, ERP integration guides, comparisons, Insights, partner directory). It also distinguishes itself from get_page by stating it returns best matches with a snippet, and from list-style siblings by emphasizing search across all these types.

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 gives a clear alternative with 'Use get_page to read a result in full' and explains language selection behavior ('English by default; set language for the Spanish, Portuguese or Chinese site'). However, it does not explicitly state when to prefer search_site over sibling list tools like list_pages or list_articles, so it lacks explicit when-not guidance.

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