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

Annotations indicate this is not read-only, not idempotent, and not destructive, but they don't explain behavior. The description adds valuable context by mentioning the return of a sessionId and shuffled cards, and the expectation of finishing with submit_review. This goes beyond the annotations, providing a clear workflow.

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, front-loaded with the primary action, and contains no fluff. Every sentence earns its place: the first states the purpose, the second covers the return value and next step.

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

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

Given the output schema exists, the description doesn't need to detail return values. It covers the purpose, return, and workflow, and the schema covers parameters. The SM-2 reference adds context about the scheduling system, making the tool's role clear within the broader study session flow.

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 does not add extra parameter details beyond what the schema already explains, but it doesn't need to since all parameters are fully described with enums and 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?

The description clearly states the action: 'Start a spaced-repetition study session for a set.' It specifies the resource (a set) and distinguishes itself from siblings like generate_cards (which creates cards) and submit_review (which records results) by describing the session-starting behavior and the return of sessionId and shuffled cards.

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

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

The description gives clear workflow context by stating 'Finish with submit_review to record results,' but it does not explicitly call out alternatives or exclusions. It implies when to use (when starting a study session) without directly comparing to sibling tools, 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?

The description goes well beyond the minimal annotations by disclosing key side effects: it reuses an existing public deck or generates a new one, marks the source as 'shared' or 'generated', and counts against monthly generation quota only when generating. This is rich, actionable behavioral information.

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, front-loaded with the core purpose, and the second sentence efficiently explains the reuse/generation logic and quota impact. No wasted words.

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 a moderate side-effect profile, the description covers the main business logic (reuse vs. generation, quota) and is supported by an output schema. It slightly lacks explicit guidance on prerequisites or error conditions, but overall is sufficient for an agent to use it correctly.

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

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

Schema description coverage is 100%, with self-explanatory parameters. The description adds no new detail about title, topic, or description beyond what the schema already states, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with a specific verb+resource pair ('Generate a flashcard deck about a topic using FlashLearnAI'), and then distinguishes the tool's unique behavior by explaining reuse of existing public decks versus generating new ones. This clearly separates it from siblings like list_sets and create_study_session.

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

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

The description gives clear context for when to use the tool: when a flashcard deck on a topic is needed. It notes the conditional reuse/generation behavior, but does not explicitly tell the agent when to prefer alternatives like list_sets or how to interpret quota before invoking.

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 readOnlyHint=true, the safety profile is known. The description adds behavioral context by specifying the scope of accessible sets and that it returns all cards with front and back text. This goes beyond the annotation without contradicting it.

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

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

Two sentences, both informative and necessary. No filler or repetition. Information is front-loaded with the primary action and resource.

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 an output schema, the description adequately covers behavior, scope, and return contents. No critical information is missing given the structured metadata.

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

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

The schema already provides 100% coverage for the setId parameter, explaining its source (list_sets or generate_cards). The description adds no additional parameter meaning, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Fetch' and the resource 'one flashcard set with all of its cards', distinguishing it from sibling tools like list_sets which lists sets. It also specifies the content (front and back text), making 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 gives useful context about when the tool works ('sets owned by the key and for public sets'), which implies when it is appropriate to use. It does not explicitly name alternatives or exclusions, but the distinction from list_sets is clear enough for effective 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?

The annotation readOnlyHint=true already signals a safe read operation, and the description goes beyond that by specifying exactly what data is shown (API calls, AI generation calls, overage calls, tier limits) and clarifying the scope (current billing period, configured API key). This adds useful behavioral context without contradicting the annotation.

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, information-dense sentence that is front-loaded with the verb and resource, and it lists specific metrics without any fluff. It earns its place entirely.

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 no parameters, a readOnlyHint annotation, and an output schema (per context), the description fully conveys the tool's purpose and the information it returns. It does not omit any critical details for a simple usage-monitoring 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?

The tool has zero parameters, so there is no parameter schema to elaborate on. The baseline for 0 params is 4, and the description appropriately focuses on the output rather than parameters, which is sufficient.

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 uses a specific verb 'Show' and clearly identifies the resource (billing-period usage and limits for the configured API key) with concrete details (API calls, AI generation calls, overage calls, tier limits). This differentiates it from sibling tools like list_sets or generate_cards, which serve different purposes.

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 implied usage is for checking current usage and limits, but the description does not explicitly state when to use this tool versus alternatives or mention any exclusions. It lacks direct guidance on when to invoke this tool instead of others.

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 readOnlyHint: true, the safety profile is already known. The description adds behavioral details beyond the annotation: ordering ('newest first'), scope ('owned by the configured API key'), and pagination behavior. It does not disclose potential failure modes or rate limits, but for a read-only list operation this is adequate.

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, front-loaded with the primary action and scope, followed by return fields and pagination. Every word serves a purpose, with no redundancy or filler.

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

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

The tool is a straightforward list operation with optional parameters and an output schema. The description covers purpose, scope, ordering, return contents, and pagination, which is sufficient for an agent to select and invoke the tool correctly. The readOnlyHint plus output schema fill remaining 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 100% for all three parameters (page, limit, source), each with descriptive text. The tool description does not add additional parameter semantics beyond what the schema already provides, so the baseline score 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?

The description uses a specific verb ('List') and identifies the exact resource ('flashcard sets owned by the configured API key'), with ordering ('newest first'). This clearly distinguishes it from sibling tools like get_set (single set) and generate_cards (creation).

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 clear context: it lists sets owned by the API key and indicates the return shape (id, title, description, card count, pagination), which helps decide when to use it. However, it does not explicitly mention alternatives or exclusions (e.g., 'use get_set for a single set'), so it falls short of full explicit 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?

The description adds context beyond the readOnlyHint and idempotentHint annotations by explicitly stating 'Makes no API call' and describing what configuration details are visible (API base URL, API key presence). This fully discloses the tool's behavior and side-effect-free nature, leaving no ambiguity.

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, front-loaded with the primary purpose, and every phrase earns its place. It avoids redundancy and is appropriately sized for the tool's simplicity.

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 health-check tool with no parameters, an output schema, and annotations covering safety, the description provides complete context. It explains what the tool does, what it returns (configuration details), and confirms it makes no API call. No additional information is needed for an agent to use 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?

The tool has zero parameters, and the description correctly does not attempt to add parameter details. Per the rubric, 0 parameters earns a baseline of 4. The schema already has full coverage (100%) with an empty parameter list, so no further explanation is needed.

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 uses a specific verb ('Check') and clearly identifies the resource (FlashLearn MCP server) and the two pieces of information retrieved (API base URL and API key status). It is immediately distinguishable from sibling tools like list_sets or generate_cards, which focus on data operations rather than server health/configuration.

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 verifying server liveness and configuration, which is a reasonable and clear context. It does not explicitly mention alternatives or exclusions, but no sibling tool serves the same purpose, so the absence of explicit when-not-to-use guidance is acceptable. A slight improvement would be stating 'use before other calls to confirm connectivity,' but the current wording is sufficient.

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=false, idempotentHint=true, and destructiveHint=false. The description adds contextual behavior by mentioning it 'Updates the SM-2 spaced-repetition schedule' and 'returns accuracy and duration stats', which are useful details beyond the annotations. No contradiction exists.

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, action-first, no unnecessary words. Every sentence contributes meaning: completion action, schedule update, and return stats.

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 annotations covering safety and idempotency, and the description explaining the side effect (SM-2 update) and return value (accuracy/duration stats), the tool is sufficiently specified for correct invocation. The sibling list provides context that this tool pairs with create_study_session.

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 covers 50% of parameters, and the description compensates partially by adding the rule 'one result per reviewed card', which clarifies the expected structure of the results array. It does not detail each field beyond the schema, but the schema already handles most fields.

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 ('Complete a study session') and the specific resource ('study session'), distinguishing it from sibling tools like create_study_session by focusing on submission and schedule update. This is a specific verb+resource pairing.

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 after a study session is created and all cards reviewed ('one result per reviewed card'), and the sibling list includes create_study_session for context. However, it does not explicitly name alternatives or exclusions, so it lacks the explicit 'when not to use' guidance.

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