D2L BrightSpace MCP

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

No annotations are provided, so the description carries full burden. It discloses that the tool downloads (writes) files and mentions user interaction (asking for path/rename). However, it lacks details on overwrite behavior, permissions, size limits, or error handling, which are important for a file download operation.

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 4 sentences with no fluff. It immediately states the purpose, then provides usage context, and ends with actionable guidelines. 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 6 parameters, no output schema, and no annotations, the description is thorough in covering purpose, usage, and parameter context. It lacks only minor behavioral details (e.g., overwrite). Overall, it is well-rounded for an agent to use 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%, but the description adds significant value: it explains the two types of file sources (course content via topicId vs dropbox via folderId/fileId) and how customFilename works. It also advises on when to use each parameter, going beyond the schema's basic 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 'Download a file from course content or assignment submissions to a local directory' with a specific verb ('download') and resource ('file from course content or dropbox submissions'). It distinguishes from sibling tools (no other download tools exist) and provides context for use cases.

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 to use this when 'the user wants to download, save, or get a file from Brightspace course content or dropbox submissions'. It includes critical guidance: 'You MUST ask the user where they want to save the file before calling this tool' and suggests suggesting a clean filename, giving concrete examples.

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 by disclosing that events carry Brightspace links, include a one-day reminder, default to unfinished work, and that output is either a saved file or inline calendar text. This is meaningful behavioral context the agent would otherwise have to guess, though file overwrite behavior is not addressed.

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 artifact produced, followed by behavioral defaults and the output-mode decision. 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?

For a self-contained export tool with no output schema and fully documented parameters, the description supplies the product format, compatibility, reminder/link behavior, default filtering, and output mode — everything needed to invoke 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 every parameter is already documented. The description adds only the practical framing of downloadPath as an absolute folder versus inline return, which is a marginal supplement rather than new syntax or defaults.

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 artifact ('Builds an iCalendar (.ics) file') plus the content scope ('upcoming assignments and quizzes'), which clearly distinguishes it from read-only siblings like get_upcoming_due_dates and get_calendar_events.

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?

Explains the default behavior (only unfinished work) and the two output modes tied to downloadPath, giving clear operational context. It does not explicitly name when to prefer this over get_upcoming_due_dates or get_calendar_events, so it falls short of full alternative 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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered and the bar is lower. The description adds only that results are "recent" with an optional course scope, without disclosing ordering, what "recent" means, pagination, or how a course-less call behaves at scale.

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, purpose front-loaded, then scope, then triggers. The middle sentence partly duplicates what the schema already states about courseId being optional, but the text is still economical with no 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?

For a zero-required-parameter read tool with a 100%-documented schema and annotations covering the safety profile, the description covers what, when, and scope. The only real omissions (ordering, recency window, pagination) are minor for a simple list tool with no output schema.

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 (count, courseId) are already fully documented in the schema, including the omitted-courseId behavior. The description restates the courseId semantics but adds no format, default, or constraint detail beyond 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 gives a specific verb+resource ("Fetch recent announcements") and states the scope (your courses, optionally one course). It stops short of distinguishing itself from adjacent retrieval siblings like get_discussions or get_whats_new, and the phrase "recent posts" slightly blurs the announcements-vs-discussions line.

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 concrete user-intent triggers ("announcements, news, updates from instructors, recent posts, or what professors said"), which is clear usage context. It names no exclusions or alternative tools (e.g., when to prefer get_whats_new or get_discussions), so it falls short of a 5.

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 openWorldHint, so safety is covered. The description adds non-obvious behavior: the two-phase invocation (list with courseId, then read with folderId+fileId) and that it returns extracted text rather than a file. It doesn't discuss auth scope or per-file size limits beyond what the schema states.

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 sentences, front-loaded with purpose, then the call pattern, then triggers, then the alternative. No filler; each sentence either routes the agent or explains a mode.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so ('Returns the text itself'), while truncation is handled by the schema's maxChars description. No output schema requirement is unmet, and no annotation gap remains for a read-only 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 coverage is 100%, so each parameter is already documented, giving a baseline of 3. The description goes further by explaining how parameters combine into two distinct modes (courseId alone lists, folderId+fileId reads one), which is workflow meaning the schema describes only per-field.

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 ('Read the files an instructor attached to an assignment') and enumerates the concrete artifact types (spec PDF, starter workbook, rubric). It also explicitly distinguishes itself from the sibling download_file, so an agent can route without opening either 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 triggers ('what an assignment requires, what the instructions say, summarize a handout') and a named alternative with its selecting condition ('Use download_file instead when the user wants the file saved to disk'). It also prescribes the two-step call pattern.

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 openWorldHint=true, so the safety profile is covered. The description adds useful content scope (due dates, status, rubric info) but says nothing about authentication, pagination, empty-result behavior, or ordering. With annotations carrying the safety burden, this is an adequate-but-thin addition.

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 with the core purpose front-loaded, then return content, then usage triggers. Every sentence earns its place and there is 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?

There is no output schema, so the description correctly compensates by describing what comes back (submissions, quizzes with due dates, status, rubric info). Combined with the annotations, an agent has enough to call it correctly; only ordering/volume behavior is unaddressed.

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 single courseId parameter is fully documented, including the default behavior when omitted. The description adds no syntax, format, or constraint detail beyond the schema, so the baseline of 3 applies.

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?

Names a specific verb and resource ('Fetch assignments and quizzes') and states the scope ('a specific course or all enrolled courses'). It also enumerates the returned artifacts (dropbox submissions, quizzes), which helps separate it from sibling tools like get_todo or get_upcoming_due_dates, though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final sentence gives concrete user-intent triggers: 'assignments, homework, what to submit, quizzes, or assignment details and rubrics.' That is clear routing context, but it offers no exclusions or alternatives, so an agent must infer why it should pick this over get_todo or get_upcoming_due_dates.

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 openWorldHint=true, so the safety profile is covered. The description adds genuinely useful scope context beyond that: it is the Brightspace course calendar, and it includes due-date events in addition to posted events, which matters given overlapping siblings like get_upcoming_due_dates. It does not cover result ordering or pagination behavior, a minor 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?

Three compact sentences: what it returns, when to call it, and which sibling to prefer instead. Zero filler and the 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?

For a read-only, no-required-param query tool with a fully documented schema and no output schema, the definition covers purpose, triggers, and the sibling boundary. The one thing not addressed is what the returned events look like or how they are ordered, which an agent might want before formatting results.

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 all four parameters (search, courseId, daysBack, daysAhead) are already documented in the schema. The description adds no extra syntax or semantics for them, so the baseline 3 applies.

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 (events from the Brightspace course calendar) and enumerates the content types it returns (exams, tests, labs, classes, office hours, due dates). It also explicitly distinguishes itself from sibling get_todo.

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 concrete trigger conditions ('when the user asks when an exam or test is, what is on their schedule, or what is happening on a day') and names the alternative to use for a different need ('for what work is left to hand in, use get_todo instead'). When-to-use and when-not-to-use are both 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 readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful return-shape context ('Returns emails only, with no names or roles'), which matters because there is no output schema. It stops short of pagination or ordering details, but the additions exceed what annotations provide.

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: purpose first, then usage scenarios, then the routing exclusion. Every sentence earns its place and the most decision-relevant 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?

For a simple one-parameter read tool, the description covers purpose, usage, return contents, and the alternative. With no output schema, the note that only emails (no names/roles) are returned closes the main gap an agent would otherwise have.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter with 100% schema description coverage ('Course ID to get emails for'), so the schema fully documents it. The description adds no syntax or format detail beyond that, which is the expected baseline when the schema does 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 description states a specific verb and resource ('Fetch all email addresses for everyone in a course') and enumerates the covered groups (instructors, TAs, students). It explicitly distinguishes itself from the sibling get_roster, so an agent can route correctly without opening either 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?

It gives concrete triggering scenarios ('needs to email the whole class', 'contact info for everyone enrolled') and names the alternative tool plus the condition that selects it ('For names, roles or finding a specific instructor or TA, use get_roster instead'). When-to-use and when-not-to-use are both covered.

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 openWorldHint=true, so safety and external-scope behavior are covered structurally. The description adds only the return shape (modules/topics/files/links), and with no output schema it does not mention pagination, size limits, or how deep an unfiltered tree may go. Useful context, but modest given the read-only operation.

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, each earning its place: purpose first, then when-to-use triggers, then the two optional narrowing parameters. Front-loaded and free of 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 no output schema, the description correctly shoulders the burden of stating what is returned (a content tree of modules, topics, files, links) and how to scope it. It stops short of describing traversal size, ordering, or truncation behavior for deep trees, but is otherwise sufficient for 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%, so the schema already documents all four parameters, making 3 the correct baseline. The description reinforces moduleTitle with filter semantics ('instead of fetching the entire tree') and maxDepth with purpose ('table-of-contents view'), adding rationale but no new syntax or format detail.

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 ('Fetch') and resource ('content tree for a course') and enumerates what the tree contains: modules, topics, files, and links. This distinguishes it cleanly from siblings like get_syllabus, get_assignment_files, or download_file, which each target a narrower resource.

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 trigger contexts ('when the user asks about course materials, lecture slides, uploaded files, content structure'), which is strong when-to-use guidance. It also advises using moduleTitle to avoid fetching the entire tree and maxDepth for a TOC view, but it never names an alternative sibling tool for overlapping needs (e.g. get_syllabus).

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 establish the safety profile (readOnlyHint=true, openWorldHint=true), so the description only needs to add operational context. It does so by disclosing how the result set expands or narrows with each parameter combination. It omits pagination, result-size, and permission behavior, which keeps it out of the top tier.

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 sentences with zero waste: purpose, usage triggers, then the three parameter combinations in increasing specificity. Front-loaded and scannable; nothing repeats the schema verbatim.

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 only three documented parameters, the description carries the return-value burden and does: it states that forumId returns topics and posts and that topicId returns all posts. An agent has everything needed to call this correctly at each level of specificity.

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. The description goes beyond the schema by explaining the interaction between forumId and topicId in terms of returned content, not just the 'requires forumId' constraint the schema states. It adds meaning rather than restating field text.

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 ('Fetch discussion board content for a course') and enumerates the sub-resources covered (forums, topics, posts). The resource is clearly distinct from every sibling tool (announcements, assignments, content, roster), so an agent can select it without cross-referencing 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 user-intent triggers ('discussion boards, forum posts, class discussions') and a precise escalation ladder: courseId alone, add forumId, add forumId+topicId. It stops short of naming an alternative tool to use instead (e.g. get_announcements for announcements), so it is clear but not fully comparative.

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 declare readOnlyHint and openWorldHint, so safety is covered; the description adds genuinely new behavioral detail about what is computed and returned (current percentage, best/worst final grade, required average) and that omitting targetPercent yields standing only. It does not discuss computation assumptions for ungraded or unweighted items, so it falls short of the top mark.

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-loaded statement of output, then concrete example queries, then the routing sentence. Every sentence carries weight, though the quoted example queries are somewhat redundant with the opening sentence.

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 fully carries the return-value burden and does so explicitly, and annotations already cover the safety profile. Usage, alternative, and outputs are all present, so nothing needed for correct invocation 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 all three parameters (including totalWeight's near-always-100 note and targetPercent's omit behavior) are already documented in the schema. The description only restates targetPercent's role via the 'must score on everything left to hit targetPercent' sentence; it adds no syntax or format guidance beyond 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?

States a specific verb and resource ('works out where the user stands in one course and what they need...') and names the sibling it is not ('For the raw grade items, use get_my_grades instead'). An agent can distinguish it from get_my_grades without opening either 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 trigger phrases ('what do I need on the final to get 80?', 'can I still pass?') and an explicit alternative for the raw-data case. Both when-to-use and when-not-to-use are covered.

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 openWorldHint=true, so the safety profile is covered. The description adds the return shape (names, codes, IDs), but says nothing about pagination, ordering, or whether inactive/future enrollments appear by default.

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 tight sentences, front-loaded with the resource and payload, followed by usage triggers. No filler or restatement of the title.

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 one-optional-param read tool with no output schema, the description covers what is fetched and when to reach for it. It could be slightly more complete by noting the default active-only filtering behavior that the schema documents.

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 single activeOnly parameter and its server-default behavior are already fully documented. The description does not mention activeOnly at all, so it adds no meaning beyond the schema; baseline 3 applies.

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 (Fetch) and resource (your enrolled Brightspace courses) and enumerates the payload (names, codes, IDs). This differentiates it cleanly from siblings like get_my_grades, get_assignments, and get_course_content without needing to open 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?

Supplies concrete trigger phrasings ("their courses", "enrolled classes", "what they're taking this semester") and routes the agent to this tool when a course ID is needed for other queries. No explicit when-not clause, but the trigger list is specific enough to drive selection.

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 openWorldHint=true, so the safety profile is covered. The description goes further by disclosing the shape of the return data (grade items with points, percentages, and comments), which matters since no output schema exists. It stays silent on error cases (e.g., invalid course ID or unenrolled course), which is a minor 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?

Three sentences, front-loaded with the core action and its scope, then return content, then usage triggers. The trigger sentence is a long enumeration but each clause is a plausible user phrasing, so little 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?

For a single-parameter read-only tool with no output schema, the description covers the operation, the default scope, the returned fields, and when to invoke it. The only missing piece is routing guidance versus the adjacent get_grade_outlook 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% and the single courseId parameter is fully documented, including the omit-to-return-all default. The description merely restates that same default ("a specific course or all enrolled courses") without adding format or constraint detail, so the baseline 3 applies.

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 ("Fetch your grade breakdown") plus the scope (one course or all enrolled courses), which is more than a tautology. It does not explicitly differentiate itself from the sibling get_grade_outlook, so the agent must infer the boundary between a raw grade breakdown and an outlook projection.

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 an explicit trigger list (grades, scores, marks, GPA, academic performance, how they're doing in a class) that maps user utterances to this tool. There are no exclusions or named alternatives, so the agent gets clear positive guidance but no disambiguation against get_grade_outlook.

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 openWorldHint, but the description adds important behavioral context: by default only instructors and TAs are returned for privacy, and includeStudents expands the result to the full class list. It also previews the returned fields (names, emails, roles).

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 followed by concise usage, default behavior, and alternative routing. Every sentence earns its place without 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 no output schema, the description provides enough return-value context (names, emails, roles), explains the privacy-sensitive default, and clarifies when to use includeStudents versus the sibling email-list tool. No critical calling information 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 all four parameters are already documented in the input schema. The description reinforces includeStudents and its privacy default, but does not add meaning beyond the schema for limit or searchTerm.

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: fetch the roster for a course. It also distinguishes the tool from the sibling get_classlist_emails by explaining that this returns richer user details while get_classlist_emails is for a plain email list.

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 names user intents that should trigger the tool, such as classmates, instructor contact info, TA emails, and professor names. It also gives the condition for using includeStudents and routes a specific alternative use case to get_classlist_emails.

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 and open-world behavior, but the description adds real value beyond them: the dual read/download behavior triggered by downloadPath, the markdown return format, and the required user-consent step before writing a file. It does not describe failure modes for an invalid courseId or a bad download path.

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 primary action and return value, with the conditional download behavior and the user-consent warning ordered by importance. There is minor overlap between the opening 'optional attachment' phrasing and the later downloadPath sentence, but nothing wasteful enough to penalize heavily.

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 what is returned (overview as markdown) and explains the file-download branch and the user-consent prerequisite. Combined with a fully documented 2-param schema and safety annotations, an agent has what it needs, though error/edge-case behavior is unaddressed.

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 are already documented. The description restates that downloadPath triggers an attachment download, which adds mild behavioral framing but no format or syntax detail beyond the schema's 'absolute path to the directory' description. Baseline 3 applies.

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 ('Fetch') and resource ('syllabus/overview text and optional attachment for a course'), and clarifies the return format (markdown overview). This cleanly separates it from siblings like get_announcements, get_assignments, or get_course_content without needing to open 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 clear conditional guidance: pass downloadPath only when the attachment should also be downloaded, plus a mandatory pre-call step (ask the user where to save). It does not name an alternative for retrieving files (e.g. the sibling download_file), so there is no 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.

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description goes further by disclosing the composition of the result set (unfinished/due-soon, overdue, not-yet-open, quizzes needing double-check, already submitted), which is genuinely useful behavioral context given there is no output schema. It stops short of noting pagination, ordering guarantees, or result caps, so it is 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?

Two sentences, zero waste: the resource plus bucket enumeration comes first, the usage trigger second, and the sibling routing last. Every clause earns its place and the most important 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?

For a read-only query tool with full schema coverage and no output schema, the description supplies everything needed: what it returns (the bucket composition), when to call it, and when to call a sibling instead. Nothing an agent needs in order to select and invoke it 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 both parameters (daysAhead, includeOverdueDays) are already documented with defaults and bounds. The description implies the concepts of 'due soon' and 'recently overdue' but adds no format, units, or interaction details beyond what the schema provides. Baseline 3 applies when the schema does 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?

States a specific resource (prioritized to-do list) and scopes it precisely across all courses, then enumerates the five buckets it contains (due soon, overdue, not open yet, quizzes to double-check, already submitted). It explicitly names the sibling it is not, so an agent can distinguish it from get_upcoming_due_dates without opening either 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 selection criteria: 'Use this first when the user asks what to work on, what's left, or what they should do now.' It also names the alternative and the condition that selects it ('For a plain chronological list of deadlines or a custom date range, use get_upcoming_due_dates instead'), 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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds genuinely new context: the enumerable submissionStatus values, that dates are UTC ISO strings, that conversion to local time is required, and that results are date-ordered. Missing pagination/limit behavior, but the added semantic detail is substantial.

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 dense sentences, front-loaded with the core purpose and with no wasted preamble. The inline enum enumeration is long but functional since no output schema exists to carry it.

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 usefully discloses the key return field (submissionStatus values) and the date encoding plus local-time conversion requirement. Combined with 100% schema coverage for inputs, an agent has what it needs; only ordering/pagination specifics are thin.

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 (courseId, daysAhead) are already fully documented in the schema. The description only implicitly gestures at them via 'all courses' and 'date ranges', adding no syntax or format 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?

States a specific verb+resource ('upcoming due dates across all courses') with clear scope and even names the sibling it is not (get_todo). An agent can distinguish it from get_assignments and export_due_dates_calendar 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 explicit usage ('for deadlines, what's due and date ranges') and routes the agent away with a named alternative and condition ('For advice on what to do first, use get_todo instead'). Nothing 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 declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral content by defining what counts as 'new' (newly marked work, unread posts, unattempted quizzes) and that the result spans all courses unless scoped. It omits return ordering, result limits, and whether sinceDays applies beyond announcements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, with the aggregate scope front-loaded before the usage triggers. Every clause carries information the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-shape burden and does so by enumerating the four result categories, which is enough to set expectations. It stops short of describing ordering, volume limits, or the fact that sinceDays is schema-scoped to announcements only, which leaves a small ambiguity for a read tool with zero required parameters.

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 courseId ('Only check this course') and sinceDays (default 7, min 1, max 30) are already documented in the schema. The description adds no parameter-level meaning beyond that, which is the expected baseline when the schema does the work.

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 — a 'catch-up summary across all courses' — and enumerates the exact categories it aggregates (announcements, unread assignment feedback, unread discussion posts, unattempted quizzes). This clearly distinguishes it from sibling single-domain tools like get_announcements, get_discussions and get_todo.

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 trigger phrases: 'what's new', 'what they missed', 'whether anything was graded or posted', and 'daily or weekly catch-up'. It does not name a when-not case or point at an alternative (e.g. use get_announcements for a single course's full announcement history), but the intended context is unambiguous.

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