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

With no annotations, the description carries the full transparency burden. It discloses bulk handling, duplicate detection, and what the return value contains (added/skipped counts and errors). However, it does not specify how duplicates are determined (e.g., by front field or entire note) or mention any environmental prerequisites like Anki being open.

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 compact and well-structured: a front-loaded summary sentence, followed by a short Args section and a Returns section. Every sentence conveys necessary information without fluff or 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?

Given the tool's moderate complexity and the presence of a nested schema and an output schema, the description covers the essential decision-making points: what the tool does, bulk behavior, duplicate handling, and return summary. Missing details like the exact duplicate detection rule and runtime prerequisites prevent a perfect score, but the description is still sufficiently complete for agent 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?

The top-level parameter 'notes' has no schema description (0% coverage), but the description compensates by stating it is a list of notes, each with front, back, tags, deck, and model. This adds structural meaning beyond the raw schema, even though the nested schema already documents each field. It does not mention defaults, but those are visible in the nested properties.

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 'Create flashcards in Anki' — a specific action verb plus resource — and adds 'bulk creation with duplicate detection,' which clearly distinguishes this from sibling tools like search_notes, update_note, and delete_notes. The purpose is unambiguous and well-scoped.

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 makes it obvious this tool is for creating notes in bulk, and the context of sibling tools implies that searching, updating, and deleting are handled elsewhere. However, it does not explicitly state 'use this instead of X' or list any exclusions, so it lacks the strongest possible 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 discloses the return value (Deck ID) and the naming convention for sub-decks, but does not mention permissions, idempotency, failure conditions, or other side effects beyond 'create'.

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 tight and well-structured with an Args/Returns format, including an inline example. Every sentence adds value 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?

For a simple one-parameter creation tool with an output schema, the description covers the core action, naming syntax, and return value. No additional context is needed for typical use.

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?

Although the input schema only defines 'name' as a string, the description adds critical semantics: the :: delimiter for nested hierarchy and an example ('AWS::IAM'). This fully compensates for the 0% schema description coverage and enriches the parameter understanding.

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

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

The description clearly states 'Create a new deck' with a specific verb and resource, and distinguishes it from sibling tools like list_decks, export_deck, and import_deck by focusing on the creation action.

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

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

The description implies usage by explaining the :: syntax for nested decks and returns, but it does not explicitly state when to use this tool over alternatives or mention any exclusions or prerequisites. It is obvious for creation but lacks 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Delete' and 'Confirmation of deletion' but does not disclose that deletion is likely permanent/irreversible, whether it cascades to associated cards, what happens if some note IDs are invalid, or if any permissions are required. The minimal wording leaves significant behavioral aspects undisclosed.

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

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

The description is exceptionally concise and well-structured. It front-loads the action, then provides an Args section and a Returns section. Every sentence serves a purpose, and there is no wasted text or repetition. This is a model of brevity.

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 delete operation, the description is minimal but lacks critical context. There are no annotations, no parameter descriptions in the schema, and no mention of side effects, error handling, or how to obtain note IDs. The output schema exists but the description's 'Confirmation of deletion' is vague. Given the tool's destructive nature and lack of annotations, the description is incomplete.

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 description says 'note_ids: List of note IDs to delete' which essentially rephrases the parameter name from the schema. Schema coverage is 0%, so the description is the only explanation, but it does not clarify what a note ID represents, how to find these IDs (e.g., via search_notes), or any constraints. It adds minimal meaning beyond the schema's array-of-integers definition.

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 ('Delete') and the resource ('cards by their note IDs'), distinguishing it from sibling tools like add_notes and update_note. However, there is slight ambiguity between 'cards' and 'notes'—the tool is named delete_notes but says it deletes cards, which could confuse users about the exact scope of the deletion.

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

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

No guidance is provided on when to use this tool vs alternatives. There is no mention of prerequisites (e.g., how to obtain note IDs), no exclusions, and no comparison with sibling tools like search_notes or update_note. The description simply states what it does without any usage context.

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

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

The description discloses a key behavioral trait: the optional deletion of the deck from Anki when archive=true. It also mentions the return value (path to the .apkg file). Since no annotations are provided, the description carries the full burden and handles it well, though it does not disclose error conditions or permissions.

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 compact docstring with Args and Returns sections. Every sentence is informative, with no redundancy or fluff, making it efficient and 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 two-parameter tool with an output schema, the description adequately covers the action, parameters, and return value. It could mention handling of nonexistent decks or configuration details, but overall it is sufficiently complete for an agent to invoke 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?

With zero schema description coverage, the description adds meaning by explaining that 'deck' is the name to export and by revealing the side-effect of 'archive' (deletes the deck). This goes beyond the bare schema property names, especially for the archive parameter.

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

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

The description clearly states the tool exports a deck to a .apkg file in the configured archive directory, using a specific verb ('Export'), resource ('deck'), and output format. This distinguishes it from siblings like import_deck, list_decks, and sync.

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

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

The description implies when to use the tool (when exporting a deck) but does not explicitly state exclusions or mention alternatives like import_deck or sync. No guidance is given for choosing this over other deck-related tools beyond the inherent distinction.

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

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

The description discloses that the operation is a read-only check and explicitly outlines the return value ('Connection status and Anki version info'). This adds context beyond the readOnlyHint annotation, such as what information the tool provides, although it does not detail error handling or connection timeout behavior.

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 extremely concise, consisting of two short sentences. It front-loads the purpose and then states the return value, with no filler or redundant text.

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

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

Given the tool's simplicity (no parameters, clear read-only operation) and the presence of an output schema, the description fully covers what the agent needs to know: what it checks and what it returns. There are no gaps in information.

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 schema already reflects that with an empty properties object. Per the rubric, a baseline of 4 applies when there are no parameters, and the description does not need to add parameter details. It adds no unnecessary clutter.

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

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

The description clearly states a specific verb ('Check') and resource ('AnkiConnect reachable') plus an additional action ('get Anki version'). It distinguishes this health-check tool from sibling tools like add_notes or sync, which perform different operations.

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

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

The description gives no explicit guidance on when to use this tool versus alternatives. It does not mention typical use cases (e.g., verifying connectivity before other API calls) or any exclusions, leaving the agent to infer usage from the name and description.

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 of behavioral disclosure. It only states that the tool imports and returns a confirmation, but does not disclose whether importing overwrites an existing deck, how conflicts are handled, or what happens if the file is missing. This is a significant gap for a mutating 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 concise and well-structured. The first sentence states the purpose, followed by Args and Returns sections. No unnecessary words, and the structure is immediately scannable.

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, simple import tool, the description covers purpose, parameter, and return value adequately. The main gap is the lack of information about conflict/overwrite behavior, which is minor given the low complexity, but it would be expected for a restorable operation.

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 provides only a string type for 'filename' with 0% description coverage. The description compensates by specifying it must be the 'Name of the .apkg file in the configured archive directory,' clarifying both the required extension and the directory context. This adds meaningful semantics 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 opens with a specific verb and resource: 'Import/restore a .apkg file from the archive directory.' This clearly distinguishes it from sibling tools like export_deck, create_deck, and list_decks. The .apkg format and archive directory add precise context.

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 'Import/restore' but there is no explicit statement of when to use this tool versus alternatives, nor any exclusions. It doesn't mention, for example, that exporting should be used to create an archive file, or that listing decks might be more appropriate for inspection.

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 readOnlyHint annotation already indicates this is a safe read operation. The description adds that it returns all decks with new/learn/review counts, but since an output schema exists, this return value information is redundant. No additional behavioral traits such as pagination, performance, or prerequisites are disclosed.

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 brief and front-loaded, stating the core function in the first sentence. The 'Returns:' section adds structure but partly duplicates what the output schema likely provides, making it slightly redundant yet still efficient.

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

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

Given the tool's simplicity (no parameters, read-only, output schema present), the description is sufficient. It covers the essential function and return contents. However, it lacks any mention of edge cases or limitations, such as how it handles many decks or whether it includes all profiles.

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 nothing to explain. The baseline for 0 params is 4, and the description does not need to compensate for any schema ambiguity since the input schema is an empty object.

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 'List all Anki decks with card counts' states a specific verb and resource, clearly distinguishing it from siblings like create_deck, export_deck, and import_deck. The scope ('all decks') and the inclusion of detailed card counts make the purpose unambiguous.

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

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

There is no guidance on when to use this tool versus alternatives. The description only states what the tool does, without mentioning any alternative tools or excluding conditions, such as 'use search_notes for specific notes' or 'use progress for study statistics.'

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 annotations declare readOnlyHint=true, and the description adds valuable context about the automatic AnkiWeb sync and the Markdown report format. It also explains the Interest Heat Score semantics, which goes beyond the bare annotation boundary.

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 well-organized with a summary, a brief explanatory note, and an Args/Returns section. The Interest Heat Score explanation adds useful context but could be tightened; overall it remains focused and efficiently worded.

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 description covers the tool's purpose, parameter meanings, return format, and a key behavioral trait (sync). Given the presence of an output schema and readOnly annotation, this is sufficient and complete for an agent to use the tool effectively.

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 input schema has no parameter descriptions (0% coverage), but the description compensates fully by explaining both 'deck' (scope to a specific deck, default all) and 'top_n' (number of tags in heat ranking, default 15). This provides complete semantics 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 opens with 'Show learning progress: deck maturity, Interest Heat Score, study consistency,' which precisely identifies the tool's function. It distinguishes itself from sibling tools like list_decks by focusing on analytical progress metrics rather than raw deck listing.

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

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

The description implies the tool is used for viewing learning progress, but it does not explicitly state when to choose it over alternatives like list_decks or sync. The sync behavior is mentioned, but there are no direct comparisons or exclusionary 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 annotation readOnlyHint=true already indicates this is a safe read operation. The description confirms this and adds return details (fields, tags, IDs), but nothing about pagination, error behavior, or rate limits. It adds some value but is not exceptionally rich beyond 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 concise and well-structured with examples, Args, and Returns sections. Every line adds value; no fluff or redundancy.

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

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

For a 2-parameter search tool, the description covers the search syntax, parameter semantics, and return values. The output schema is present, so return format does not need further elaboration. It is complete for the tool's 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 descriptions cover 0% of the parameters, so the description must carry the full burden. It fully explains 'query' as an Anki search query string with multiple examples, and 'limit' as max results with a default. This adds meaning well beyond the bare schema type definitions.

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 ('Search for existing cards') and the resource ('using Anki query syntax'), with concrete examples. It distinguishes this from sibling tools like add_notes, update_note, and delete_notes, which are clearly write operations.

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 this tool (searching existing cards) and provides syntax examples that imply usage patterns. However, it does not explicitly state when not to use it or name alternative tools like list_decks for deck-level queries.

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 must disclose behavior. It mentions the return value ('Confirmation that sync completed') but does not describe network dependencies, potential side effects on local data, or error conditions. It adds some transparency but lacks depth.

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 extremely concise, with a clear action statement followed by a return value note. No redundant wording or unnecessary detail.

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-parameter sync tool, the description adequately covers the purpose and expected return. The presence of an output schema mitigates the need for detailed return descriptions. Minor omissions like preconditions or failure modes prevent 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?

The tool has zero parameters, so the schema is fully covered. The description does not need to explain parameters, and it correctly omits them. Baseline of 4 is appropriate given the absence of parameters.

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 with a specific verb and resource: 'Trigger AnkiWeb sync.' This is distinct from sibling tools like add_notes or list_decks, leaving no ambiguity about what the tool does.

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

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

The description provides no explicit guidance on when to use this tool vs alternatives. It simply says to trigger sync, leaving the situation to the agent's judgment. However, since none of the siblings perform synchronization, it is not misleading, just minimal.

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

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

With no annotations provided, the description carries the full burden. It usefully discloses that tags 'replaces all existing tags' and mentions a return confirmation, but it does not explicitly clarify whether omitted front/back fields are preserved or how invalid note_ids are handled. This leaves some ambiguity in behavior.

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 concise and well-structured with a clear summary line followed by Args and Returns sections. Each parameter is described succinctly with optionality markers, and no unnecessary words are present.

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 description covers the core workflow, parameter semantics, and the key tag-replacement side effect. Since an output schema exists, detailed return value documentation is not strictly necessary. It lacks error handling details, but for a straightforward update tool, this is acceptable.

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 provides no descriptions (0% coverage), so the description fully compensates. It explains each parameter's purpose: note_id's source, optionality of front/back, and the replacing behavior of tags, adding valuable meaning beyond the raw schema types.

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 'Edit an existing card's fields or tags' with a specific verb and resource. It distinguishes itself from sibling tools like add_notes, delete_notes, and search_notes by focusing on updating existing notes.

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 by specifying that note_id comes 'from search_notes results', implying a workflow. However, it does not explicitly state when not to use this tool or compare it to alternatives, so it falls short of a perfect score.

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