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

With no annotations, the description carries the full transparency burden. It discloses the sequence (open, wait, verify, save, close) and mentions 'owner-only session state,' which hints at file writes. However, it omits critical behavioral details: it does not state that interactive MFA may be required, that Chrome will close disrupting other tabs, or any failure/timeout behavior. This is a moderate gap.

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 purpose and outlines the entire workflow with zero wasted words. It is concise, readable, and efficiently conveys the tool's core function.

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 tool's moderate complexity (3 parameters, no output schema, no annotations), the description is incomplete. It does not explain parameter usage, nor does it specify the return value or success/failure indicator, and it lacks explicit mention of user interaction needs (MFA). An agent would struggle to invoke it correctly without additional documentation.

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 compensate. It only indirectly references 'wait one minute by default' (matching initialWaitSeconds default), but never names or explains timeoutSeconds or pollIntervalSeconds. The agent cannot infer parameter meaning from the description, which is a clear deficiency.

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 ('Authenticate'), a clear resource ('SMU eLearn'), and describes the full process (open Chrome profile, wait, verify, save state, close). It is immediately distinct from all sibling tools, which focus on documents/courses, not authentication.

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 provides no guidance on when to use this tool versus alternatives like elearn_auth_status, nor does it state preconditions (e.g., must be logged out, or must run before other tools). It implies usage only through its purpose, leaving the agent to infer when authentication is needed.

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 no annotations, the description carries the burden of behavioral disclosure. It states the tool checks authentication, which implies read-only behavior, but does not explicitly mention non-mutating characteristics or the return format. Given the simplicity of the tool, this is adequate but could be more explicit.

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, clean sentence that directly states the tool's purpose without any fluff or redundancy. It is front-loaded and efficient, earning a top score.

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 tool with no parameters and a simple status-check function, the description is largely complete. However, it does not mention the return value or output format, which could be useful for an agent. Since there is no output schema, a brief note on what is returned (e.g., boolean) would improve completeness, but it is not critical.

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 tool has zero parameters and an empty schema (100% coverage). According to the calibration rule, a baseline of 4 applies for zero-parameter tools, and since there are no parameters to document, the description adds no additional semantic burden.

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 ('Check') and resource ('whether the dedicated Chrome profile is currently authenticated with SMU eLearn'), which clearly identifies the tool's function. It is distinct from sibling tools like elearn_authenticate, which performs authentication rather than checking it.

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 clearly implies a status-check use case without explicit exclusions or alternatives. It does not name sibling tools or provide 'when not to use' guidance, but the purpose is unambiguous enough that an agent would know to call this before deciding whether further actions are needed.

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 a key behavioral trait: existing files are never overwritten and a numeric suffix is added. This is useful and not covered by annotations (none provided). It also implies the destination is configurable. However, it does not mention error handling, return values, or the exact file naming scheme, but the disclosed behavior is a significant safety-relevant detail.

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 zero redundancy. The key action and the critical overwrite behavior are front-loaded, and every word 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 there is no output schema and no annotations, the description should cover what the tool returns, error conditions, and how IDs are obtained. It only states the action. It lacks crucial information for an agent to confirm success or handle failures, and does not mention whether the download is synchronous or asynchronous.

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 only 25% (only destinationDir has a description). The description does not explain the parameters courseId, topicId, or filename, nor how they relate to the download. It mentions 'configured local download directory' but doesn't clarify that destinationDir is an optional override. The description fails to compensate for the low 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 states a specific verb ('download') and resource ('file topic') and indicates the destination (local download directory). It is clear and distinct from the sibling get/search tools, though it does not explicitly name alternatives. The main gap is that it doesn't mention what a 'topic' is or how to obtain the IDs, but the core purpose is unambiguous.

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 no guidance on when to use this tool versus alternatives, nor does it mention prerequisites like authentication (sibling authentications exist) or when not to use it. It is implied that you need courseId and topicId from other tools, but not stated. No exclusions or routing to 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?

With no annotations provided, the description carries the full burden of disclosing behavior. It states the tool returns 'all accessible file topics' recursively, implying permission-based filtering, and mentions the returned metadata (module paths, dates). However, it does not disclose authentication requirements, confirm read-only nature, or address potential error conditions. The term 'accessible' hints at filtering but lacks explicit detail on hidden or link handling, leaving partial transparency.

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, concise sentence of approximately 20 words. It front-loads the action and key return contents, avoiding unnecessary detail. While it omits parameter explanations, that is a completeness issue, not a conciseness one. The structure is clean and scannable, earning a high score for efficiency.

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 three parameters, no output schema, no annotations, and zero schema coverage. The description states the primary function but fails to explain the optional flags (includeLinks, includeHidden), any pagination or sorting defaults, or selection criteria relative to sibling tools. It is not sufficiently complete for an agent to invoke correctly without additional schema inspection.

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%, and the description does not explain any of the three parameters (courseId, includeLinks, includeHidden). It omits how these parameters affect output or defaults. The description entirely misses parameter semantics, forcing the agent to rely solely on parameter names, which is inadequate for optional flags like includeLinks and includeHidden.

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 returns all accessible file topics in a course, recursively, with module paths and availability/modified dates. It uses a specific verb ('Return') and a specific resource ('file topics in a course'), making the purpose evident. However, it does not explicitly differentiate from sibling tools like elearn_get_week_documents or elearn_search_content, leaving the distinction implicit.

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 provides no guidance on when to use this tool versus its siblings. It does not mention alternatives, prerequisites, or scenarios where this tool is preferred over elearn_get_week_documents or elearn_search_content. The agent must infer usage context from the name and description alone, which is insufficient.

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 no annotations provided, the description carries the full burden of behavioral disclosure, yet it says only 'Get,' which implies a read operation without confirming it. It discloses nothing about authentication requirements (notably relevant given elearn_authenticate and elearn_auth_status siblings), the structure or extent of the returned metadata, failure behavior, or rate limits.

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 clean, front-loaded sentence with no wasted words, which is structurally sound. However, it leans toward under-specification rather than deliberate conciseness, delivering little information beyond what the name and title already convey.

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?

While the tool is simple (two scalar params), the 0% parameter coverage, absent output schema, and missing annotations mean the description must carry more weight. It omits parameter semantics, auth requirements, and return-value expectations, leaving an agent without enough information 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 description coverage is 0%, so the description must compensate, but it mentions no parameters at all. It does not clarify the semantic difference or hierarchy between courseId and topicId, or how they identify the target document. The description adds zero value for parameter understanding.

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 ('Get') and a specific resource ('D2L content-topic metadata for one course document'). The 'metadata' qualifier and 'one... document' scope clearly separate it from elearn_download_document (which fetches content) and elearn_search_content. It is fairly clear, though it does not explicitly distinguish itself from elearn_get_course_documents, which might also return metadata for documents.

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?

No guidance is given on when to use this tool versus its siblings. It does not state when to prefer this over elearn_get_course_documents, elearn_get_week_documents, or elearn_search_content, nor any exclusions or prerequisites such as prior authentication. Usage context is only weakly implied by the phrase 'one course document.'

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 no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the default time window (Monday through Sunday in local time) and the default scope ordering (pinned, all, explicit IDs), which is useful. However, it omits many behavioral aspects like pagination, result format, handling of hidden/removed items, or authentication requirements. The description provides some transparency but leaves significant gaps.

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, tightly packed with essential information. The main purpose is up front, followed by the default time window. There is no filler or redundant wording, making it efficient for agent consumption.

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 7 parameters, no output schema, and no annotations, the description is too sparse. It does not explain return values, limits (maxCourses), behavior of includeLinks/includeHidden, or how results are ordered/sorted. An agent would need to guess many call details. The description does not sufficiently prepare an agent to use the tool correctly without additional exploration.

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 43%, so the description must compensate for undocumented parameters. It adds context for 'scope' (pinned/all/explicit course IDs) and clarifies that courseIds override scope. However, it doesn't explain maxCourses, includeLinks, or includeHidden, whose schemas lack descriptions. The description adds moderate value but doesn't fully cover the parameter semantics gap.

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 searches file topics by D2L LastModifiedDate, with specific scope options (pinned, all active, explicit course IDs). It distinguishes itself from course-specific tools by mentioning multiple course scopes, but doesn't explicitly contrast with sibling tools like elearn_get_week_documents. The verb 'Search' and resource 'file topics' make the purpose specific.

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?

No explicit guidance on when to use this tool versus alternatives. It mentions the default behavior (pinned courses, current week) but doesn't state when to choose this over elearn_get_week_documents or elearn_get_course_documents. Agents must infer usage from the scope options without clear decision criteria.

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?

No annotations are provided, so the description must disclose behavior. It mentions 'recursively' and 'accessible', which gives some behavioral context, but it does not cover pagination, error handling, or implications of includeLinks/includeHidden beyond the schema. It's clearly read-only but that's implicit.

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, efficient sentence that front-loads the core purpose, followed by a brief clarification of the week parameter. There is no fluff or 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?

With 4 parameters, no output schema, and no annotations, the description is thin. It doesn't clarify what 'accessible' means, whether results are paginated, or how this tool differs from elearn_get_course_documents. It would benefit from a note about when to prefer this over siblings and what the response structure looks like.

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 minor context by explaining the week parameter can be a number or title fragment, which the schema already states. It does not add depth to courseId, includeLinks, or includeHidden beyond the 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 clearly states the action ('Return'), the resource ('every accessible file topic'), scope ('for one course'), and specificity ('matching Week modules', 'recursively'). It distinguishes itself from siblings like elearn_get_course_documents or elearn_get_recent_documents by focusing on week-based retrieval.

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 the use case (retrieve documents for a specific week) but does not explicitly state when to use this tool versus alternatives like elearn_get_course_documents or elearn_search_content. No exclusions or routing hints are provided.

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?

No annotations are provided, so the description must disclose behavioral traits. It mentions the output fields but does not state whether authentication is required, whether it is read-only, or any rate limits or pagination behavior. The word 'List' implies a read operation, but this is implicit rather than explicit.

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 no filler. It front-loads the core action and then adds useful output details. Every word earns its place, making it efficient and well-structured.

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 absence of an output schema and annotations, the description is too sparse. It does not mention authentication prerequisites (a sibling 'elearn_authenticate' exists), pagination behavior, or how the 'limit' parameter affects results. The listed output fields provide some context but not enough for an agent to fully understand the tool's expected usage.

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 covers 75% of parameters with descriptions (search, activeOnly, pinnedOnly), but the description adds no parameter-specific guidance. The 'limit' parameter lacks a schema description and is not mentioned in the description either, leaving a gap. The mention of 'pin state' in the output hints at the pinnedOnly filter but does not explain how to use it.

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 ('List') and resource ('accessible SMU eLearn courses'), and enumerates the output fields (course IDs, codes, term dates, access state, pin state). This is clear and specific, but it does not explicitly differentiate from the sibling tool 'elearn_list_pinned_courses', though the name and filters imply a more general listing.

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 provides no guidance on when to use this tool versus alternatives like 'elearn_list_pinned_courses' or when to prefer one filter over another. It simply states what it does without any context on selection criteria or exclusions.

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 no annotations provided, the description carries the full burden for behavioral disclosure. It mentions what information is reported but does not explain any side effects (e.g., read-only vs. mutation), authentication requirements, how the includeLinks and includeHidden parameters alter behavior, or potential error conditions. The description adds some context about the naming pattern but leaves significant behavioral aspects undisclosed.

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 is direct and free of unnecessary words. It front-loads the core behavior ('Find nested course-content modules...') and then lists the reported attributes. There is no redundancy, and every phrase contributes to understanding the tool's purpose.

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 tool has three parameters (two undocumented), no output schema, and no annotations, the description should provide more context about how parameters affect results and what the return structure looks like. It only vaguely states that IDs, paths, dates, and document counts are reported, but doesn't specify the format, pagination, or how includeLinks/includeHidden change the output. The description is too sparse for an agent to fully anticipate the tool's behavior.

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 33%, with only courseId having a descriptive text. The other two parameters, includeLinks and includeHidden, have no schema descriptions. The tool description does not compensate for this: it doesn't explain what these flags do, whether they affect filtering or output, or how they interact. For an agent to correctly set these parameters, additional meaning is needed but absent.

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 function: it finds nested course-content modules named with Week/Wk/W followed by a number and reports specific fields (IDs, paths, dates, document counts). This is a specific verb-resource pair that differentiates it from sibling tools like elearn_get_week_documents, which likely retrieves documents for a given week. The naming pattern and reported fields make the purpose unambiguous.

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 by describing what it does (finding weeks), but it does not explicitly mention when to use this tool versus alternatives, nor does it state any exclusions or prerequisites. There is no guidance on when not to use it or when a different tool might be more appropriate, so it falls short of the 'explicit when/when-not' standard.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It mentions ordering but does not state whether the operation is read-only, requires authentication, handles pagination, or what error behaviors might occur. The description stays at the surface level and does not go beyond what the name implies.

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, efficient sentence that directly conveys the purpose without fluff. It is appropriately concise and well-structured for a simple list operation.

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 tool with two parameters and no annotations, the description is incomplete. It fails to explain the 'limit' and 'search' parameters, does not mention authentication requirements, and provides no information about the response format or potential errors. Even for a simple listing tool, these gaps could lead to incorrect invocation (e.g., passing an overly large search string or misinterpreting the ordering).

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 has no descriptions (0% coverage) and the description does not mention the parameters 'limit' or 'search' at all. An agent must rely solely on parameter names, which are somewhat self-explanatory but not fully defined. The description adds no value in explaining semantics, constraints, or how these parameters affect results.

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 action ('List'), the resource ('courses pinned by the current user'), and adds ordering criteria ('by pin date and course name'). It distinguishes itself from sibling tools like elearn_list_courses by specifying 'pinned by the current user'.

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?

No guidance is given on when to use this tool versus alternatives such as elearn_list_courses or elearn_search_content. The description implies it is for pinned courses only, but does not explicitly exclude other scenarios or mention any prerequisites like authentication. Contextual signals like sibling tool names could help, but the description itself offers no 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 no annotations, the description carries full responsibility for behavioral disclosure. It only explains what is searched (titles and module paths) but does not mention authentication requirements, result ordering, fuzzy vs. exact matching, or any side effects. For a search tool, this is a minimal disclosure that leaves significant behavioral unknowns.

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?

A single, front-loaded sentence that efficiently conveys the core function and scope options. No wasted words, and the most important information (what is searched) appears first.

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 6 parameters, no output schema, and no annotations, the description is far from complete. It does not explain parameter defaults, result format, or prerequisites like authentication. An agent would need to consult external documentation or make assumptions to use 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 description coverage is 0%, so the description must compensate. It explains the 'scope' and 'courseIds' concepts (pinned, all, explicit course IDs) and hints at query semantics (titles, module paths), but completely ignores 'limit', 'maxCourses', and 'includeLinks'. For a tool with 6 parameters, this is insufficient semantic guidance.

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 a specific verb 'Search' and resource 'document titles and module paths', and explicitly mentions the three scope options (pinned, all, explicit course IDs). This distinguishes it from sibling tools that retrieve documents by week or course, and leaves no ambiguity about its function.

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 for searching across courses, but does not explicitly state when to use this tool versus alternatives like elearn_get_week_documents or elearn_get_course_documents. It lacks direct guidance on exclusions or preferred scenarios, leaving the agent to infer context from the tool's purpose.

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