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

With no annotations, the description carries the full burden. It discloses the return payload (description and enrollment code), which is genuine behavioral information, but says nothing about failure modes (invalid/unknown id), permissions, or authentication requirements.

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 lines: purpose first, then the parameter note. No filler, nothing repeated from the schema's structured fields.

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 one-parameter read tool with no output schema and no annotations, the description covers the essentials: what is fetched, what comes back, and where the id originates. Only error/empty-result behavior is unaddressed, which is a minor gap at this complexity.

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

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

Schema coverage is 0%, so the description must compensate — and it does, documenting the single parameter's provenance ('from list_courses') and its format ('numeric string'). That is meaningful semantics the bare string-typed schema does not supply.

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 ('Get one course by id') and names the fields returned (description, enrollment code). It is distinguishable from the list_* siblings by being singular and by pointing at list_courses as the id source, though it never explicitly contrasts itself.

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?

Usage is implied rather than stated: the note that course_id comes from list_courses suggests the retrieve-after-list flow. There is no explicit when-to-use/when-not-to-use guidance or mention of alternative ways to reach course data.

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 bears the full behavioral burden. It hints at a recency window via 'Recent' but never defines it, and says nothing about ordering, pagination, whether results are read-only, or permission requirements for the course.

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 single line followed by a compact args block; nothing is padded. Minor duplication of schema field names in the Args section, but it costs little.

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 two-parameter read tool with no output schema, the description is minimally viable, but the undefined 'recent' window and absent return/ordering notes leave gaps an agent may need to probe for.

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, and it does document both parameters — notably the useful cross-reference that course_id comes from list_courses. The limit explanation restates the parameter name rather than adding meaning (e.g., default, cap, or paging behavior).

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 the resource (announcements) and scope (for a course) clearly enough that an agent knows what it returns. It is the only announcements-oriented tool among the siblings, so no explicit differentiation was needed, but the phrasing is nominal rather than a verb+resource statement.

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 when-to-use guidance, no prerequisites, and no alternatives named. An agent cannot tell from the description when this should be preferred over the other list_* tools or what conditions limit its usefulness.

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 full burden. It usefully discloses that results are scoped to the signed-in account and cover both teacher and student roles, but it says nothing about pagination, result limits, ordering, or required OAuth scopes for a list operation that can grow large.

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 purpose sentence is front-loaded and the parameter note is compact and free of padding. Slightly more structure than needed for a one-parameter tool, but nothing wasteful.

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 single-parameter read tool with no output schema and no annotations, this is close to sufficient, but a listing tool should mention pagination behavior or a result cap so the agent knows how to retrieve everything. That omission is the main remaining gap.

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 and largely does: it explains course_states is optional, gives the full value set (ARCHIVED, PROVISIONED, DECLINED, SUSPENDED alongside ACTIVE), and notes that multiple values can be combined. The only gap is the stated default ["ACTIVE"] differing from the schema's null default.

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 ("List Google Classroom courses") plus the scope ("for the signed-in account") and the two role perspectives covered (teacher or student). This clearly distinguishes it from siblings like get_course or list_coursework, though it doesn't name those alternatives.

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?

Usage is implied by the verb and the account scoping, but there is no explicit guidance on when to use list_courses versus get_course for a single course, nor any note about when archived/provisioned states should be requested. Adequate but leaves selection logic 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?

No annotations are provided, so the description carries the full burden. It does disclose one genuine behavioral trait beyond the schema: results default to PUBLISHED-only unless states is widened. It omits pagination behavior, ordering, and auth requirements, which is a notable gap for a list endpoint with no 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 purpose line is front-loaded and the three argument notes are terse and each earn their place. The Args block formatting is slightly verbose for only three parameters, but nothing 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?

With no annotations and no output schema, the description is the only source of behavioral context. It identifies the returned item types, which partly covers the return shape, but gives no pagination, ordering, or truncation semantics for a list tool — enough to call it, not enough to use it confidently.

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, and it does: course_id is sourced ('from list_courses'), states is explained with its default and permissible values, and limit is described as a maximum item count. It lacks format details (e.g., whether states combines as OR, limit bounds), so it stops short of a 5.

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 (List) and resource (coursework) and even enumerates what counts as coursework (assignments, quizzes, questions, materials), scoped 'for a course'. It does not explicitly contrast itself with siblings like list_courses, though the course_id reference to list_courses makes the hierarchy inferable.

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?

Usage is implied: call this to enumerate coursework within a course. The states note ('Defaults to ["PUBLISHED"]; can include "DRAFT" or "DELETED"') gives useful filtering context, but there is no explicit when-to-use vs alternative or exclusion 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?

With no annotations, the description carries the full burden. It does disclose useful behavior beyond the schema: results are sorted by due date and limited to active courses. However, it says nothing about read-only nature, result volume, pagination, or what happens to courses not marked active.

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

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

Front-loads the one-line purpose, then uses a compact Args block. The parameter restatement is justified because the schema has zero description coverage, though it is slightly terse on format details.

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 two-parameter read tool with no output schema and no annotations, the description covers purpose, scope, ordering, and both parameters adequately. It stops short of describing return shape (e.g., coursework fields, grouping by course) or result limits, which an agent would benefit from.

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, and it does: 'days' is defined as a look-ahead window with a stated default, and 'include_overdue' is explained as also returning items whose due date has passed. Only minor gaps remain, such as whether 'days' counts from now and how overdue items interact with the window.

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 concrete verb+resource ('Upcoming coursework across all active courses') plus ordering ('sorted by due date'), so the agent knows it is a scoped, time-windowed list rather than a generic coursework fetch. It does not explicitly name list_coursework as the unfiltered alternative, so differentiation from siblings is only 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 'upcoming' framing implies the intended context, but there is no explicit statement of when to use this over list_coursework, nor any prerequisite or exclusion guidance. The agent must infer the choice from the tool name and the first sentence alone.

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 carries the full burden. 'List' plus the return-content disclosure (names and emails) establishes this as a read, and the course_id provenance is useful. However, it says nothing about permissions, pagination, or what happens with an invalid course_id.

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 short lines, front-loaded with the resource and return fields before the argument note. No wasted prose, though the 'Args:' block is slightly formal for a single parameter.

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 one-parameter read tool with no output schema and no annotations, the description covers the essentials: what it returns and where the argument comes from. Missing pagination/volume and error context keeps it from a 5.

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% — the schema only says 'Course Id'. The description compensates by identifying the argument's source ('Course id from list_courses'), which is real value beyond the schema. It does not describe the id's format or failure behavior, so not a 5.

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 and scope ('student roster for a course') and discloses the returned fields (names and emails), which distinguishes it from siblings like list_teachers or list_submissions. It does not explicitly name or contrast with those siblings, so it falls short of a 5.

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?

Usage is only implied: the tool is clearly for enumerating a course's students, and the note that course_id comes 'from list_courses' hints at the prerequisite call. There is no explicit when-to-use vs when-not-to-use guidance or named alternative.

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 carries the full behavioral burden. It implies 'submission state and grades' are returned but does not disclose auth requirements, pagination behavior, whether the limit truncates or throttles, or the default user scoping beyond what is in the schema. For a read tool with zero annotation coverage, this is a significant 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?

One-line purpose followed by a structured Args block. Efficient, though the purpose sentence omits an explicit verb and relies on the name for action. No wasted sentences.

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?

Covers parameters well and states the return content at a high level, but for a read tool with no annotations and no output schema, it omits auth requirements, pagination/limit semantics, and error behavior. Adequate but with clear 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?

Schema description coverage is 0%, so the description must compensate, and it does: user_id explains the 'me' default, numeric id/email forms, and the teacher-only '-' value; limit is defined as maximum submissions; course_id and coursework_id are traced to their source tools. This meaningfully exceeds the bare schema titles.

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 and scope: submission state and grades for one assignment. The verb is implicit ('list') matching the name. It clearly distinguishes itself from sibling list_* tools by naming the assignment-submissions domain, though it does not explicitly contrast with list_students or list_coursework.

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 when-to-use or when-not-to-use guidance. It implies teacher/student context via the '-' value but does not state that listing all students requires teacher privileges as a selection condition, nor does it point to alternatives.

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 carries the full burden. It discloses the returned fields (names and emails), which is useful behavioral context, but says nothing about read-only safety, permissions/privacy constraints on student-teacher data, result ordering, or pagination.

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 purpose line is front-loaded and waste-free, and the Args block is terse. The block is slightly redundant with the schema, but with 0% schema coverage it 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?

For a single-parameter, no-output-schema list tool this is close to complete: the agent knows what it returns and where the id comes from. Only pagination/ordering behavior and any access constraints are 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 0%, so the description must compensate, and it does: it names the single parameter and tells the agent where the value comes from (list_courses), which is the key semantic an agent needs. It stops short of format/validation details, but the core meaning is added.

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 (list) and resource (teachers), plus the payload returned (names and emails) and its scope (for a course). It is distinguishable from list_students by resource, but it does not explicitly differentiate itself from that sibling or from get_course.

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?

Usage is implied: this is the roster tool for a course, and the arg note points the agent to list_courses to obtain the required id. There is no explicit statement of when to prefer this over list_students/get_course or of any prerequisite conditions beyond the id source.

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