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

With no annotations, the description carries the full behavioral burden, and it does disclose meaningful traits: it is write-only ('Firestoreへの書き込みだけを行う'), the structuring logic is Claude's responsibility, depth is arbitrary rather than fixed at 3, and only existing maps are valid targets. However, it omits permissions/auth requirements, error or failure behavior, and reversibility of the write.

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 is front-loaded, followed by the depth-flexibility note, the division-of-labor clarification, and prerequisites. Every sentence contributes, though the density makes it slightly harder to parse than an ideal definition.

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 3-parameter write tool with no output schema and no annotations, the description covers purpose, prerequisites, parameter sourcing, and the non-obvious division of labor. It lacks only return/error behavior, which is a minor gap given the absence of an 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 the baseline is 3, but the description adds genuine decision guidance beyond the schema: parentElementId should be derived by inspecting list_elements output, and mapId comes from list_maps. These are procedural instructions the schema alone does not provide.

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 names a clear verb+resource — adding Claude's hierarchical thought structure into an existing map — and explicitly distinguishes itself from create_map ('対象は既存マップのみ...新規作成が必要ならcreate_mapを先に呼ぶ'). It is less clear about how it differs from other write-oriented siblings like edit_element or import_markdown_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?

It gives concrete routing guidance: look at list_elements results to decide parentElementId, and call create_map first if a new map is needed. That is an explicit alternative and prerequisite. It stops short of stating when NOT to use this tool versus sibling write tools.

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, and it does add real behavioral context: a mandatory user-confirmation step and an explicit prohibition on autonomous creation. It does not describe the success/duplicate/error behavior of the create itself, so it falls short of fully covering the write semantics.

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, with the primary action stated first and the guardrails (list_maps check, user confirmation) following in priority order. No filler 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 simple two-required-parameter create tool with no output schema, the definition covers the purpose, precondition, and confirmation workflow. It is nearly complete, though it could note what happens on success or when a duplicate title is used.

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 'title' and 'isTodo' are already documented in the schema, and the description adds no additional syntax or format detail beyond them. Per the baseline rule for high coverage, a 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 states a specific verb and resource ('新しいマインドマップを1つ作成する'), specifying cardinality ('1つ'). It is immediately distinguishable from siblings like list_maps, edit_element, or delete_elements.

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 explicit routing rules: call only after list_maps confirms no matching map exists, and require a user-confirmed title proposal first. The alternative (list_maps) and the precondition are both named, 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?

With no annotations, the description carries the full behavioral burden and does well: it discloses irreversibility (削除は取り返しがつかない), cascade deletion of descendants, and the dry-run semantics of confirmed, including that the dry run returns the paths and descendant counts. It stops short of stating permission requirements or limits on how many elements may be deleted at once.

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 destructive action and cascade scope, then the safety workflow. Every sentence carries required information and nothing is padded.

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 destructive, annotation-free tool with no output schema, the description supplies the missing safety profile and explains what the dry-run returns (paths and descendant counts). An agent has everything needed to call it safely and 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%, so the schema already documents mapId, elementIds and the dry-run meaning of confirmed. The description restates the confirmed workflow rather than adding syntax, format, or edge-case detail beyond it, so the baseline 3 is right.

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 ('既存マップから要素を削除する') and immediately clarifies scope via the cascade rule (指定した要素とその配下(子孫)を丸ごと削除する). This clearly separates it from siblings like edit_element and move_element, which touch the same resources without removing them.

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?

Prescribes an explicit two-call workflow: first call with confirmed omitted/false to obtain the target list, present it to the user for explicit consent, then re-call with confirmed: true. The when-not condition (do not delete before consent) and the alternative call mode are both spelled out.

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 usefully scopes the mutation to the detail field only and implies check state and element count are untouched, but it says nothing about required permissions, whether the previous detail is recoverable, or failure behavior on a missing mapId/elementId. Adequate scoping, incomplete mutation semantics.

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 first states what is changed and at what granularity, the second handles dispatch to siblings. Front-loaded and appropriately sized for a 3-parameter mutation tool.

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 mutation tool with no annotations and no output schema, the description covers scope and sibling routing but leaves permissions, reversibility, and error/response behavior unstated. It is callable without ambiguity because the schema is fully documented, but the behavioral envelope is 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 description coverage is 100% – each of the three parameters is documented inline, including the list_maps/list_elements provenance for the IDs and minLength on detail. The description adds no format or constraint detail beyond that, 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 in one clause: it rewrites the detail body of a single existing map element. It also names the sibling tools that handle the adjacent operations (adding elements, toggling check state), so the agent can distinguish it from auto_structure_thought, import_markdown_context and update_task_status without opening 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?

Explicitly routes the agent: element creation belongs to auto_structure_thought / import_markdown_context, and check-state changes belong to update_task_status. This gives both when-to-use and when-not-to-use with named alternatives, which is exactly what a crowded sibling set (8 tools) needs.

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, and it does disclose real quirks: headings become elements, and checkbox syntax/state is stripped for non-TODO maps. However, it does not say whether the import appends to or replaces existing map content, whether the operation is idempotent or reversible, or what happens on invalid mapId — notable gaps for a mutation tool.

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 core action and format expectations are front-loaded in the first sentence, followed by the behavioral exceptions. It is dense but each sentence adds a distinct rule; only minor phrasing could be tightened.

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 3-parameter mutation tool with no annotations and no output schema, the description covers format, tree semantics, and prerequisites well, but omits append-vs-replace semantics and error/return behavior. It is adequate but leaves the agent guessing on state-changing side effects.

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 mapId, markdown, and parentElementId are already documented in the schema. The prose adds only the implicit idea that content lands inside parentElementId (or at top level if omitted), matching what the schema already says, so the 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?

The description names a specific verb (build/stream Markdown into a map) and resource (an existing map), and immediately clarifies the flattening rule that headings count as elements. It is clearly distinguishable from siblings like create_map and edit_element because it operates on a whole Markdown tree rather than single elements.

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 explicitly states the target must be an existing map and names the alternative ('if you need a new one, call create_map first'), which routes the agent correctly. It also gives the condition under which checkbox notation is dropped, though it does not discuss when to prefer this over editing elements individually.

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 behavioral burden and does so richly: it discloses the confirmation gate (calling without confirmed returns a prompt instead of data), the confidentiality risk of map contents, and the staleness behavior that memory shouldn't be trusted. These are exactly the non-obvious traits an agent needs before invoking.

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?

Return values and the raw-checked caveat are front-loaded, and every sentence carries actionable information. It is dense but never padded, though the single long block could be broken up for faster scanning.

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 adequately describes the return shape (elements, parent-child structure, checked state) plus the gating and staleness behavior. An agent has everything needed to call it correctly and interpret 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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema by explaining the operational semantics of confirmed (must ask the user first, never set true before confirming) and the meaning of mapId's source. This adds real meaning over the field descriptions rather than restating them.

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?

Opens with a specific verb+resource+scope: returns all elements in a given map along with parent-child relationships and checked state. It further sharpens the deliverable by clarifying that checked is the raw stored value, not an inherited-completion interpretation, so an agent knows exactly what it gets versus related read tools like list_maps.

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 conditions: obtain the user's own consent before reading an unfamiliar map, and re-call this tool (never rely on memory) whenever the user asks about progress or state because app-side edits are not reflected until invoked. It also states the exact invocation protocol (call without confirmed to get a prompt, then re-call with confirmed: true).

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 and does well: it discloses that results include both owned and shared maps, that 'viewer' role implies read-only with no write tools available, and that app-side edits are not reflected until this tool is re-called. It does not cover return ordering, pagination, or limits, which keeps it short of 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?

Four sentences, entirely front-loaded with what is returned and the prerequisite that a call is needed before using mapId elsewhere. Each subsequent sentence adds a distinct, non-redundant constraint (shared-map visibility, viewer read-only, state freshness).

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 list tool with no output schema and no annotations, the description supplies everything needed: return contents, the prerequisite sequencing relative to other tools, the shared-map permission caveat, and the freshness warning. Nothing an agent needs in order to call 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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline of 4 applies. The description usefully enumerates the fields returned (title, ID, TODO flag) even though they are not inputs.

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: returns all of the user's Matryoshka Mind Maps with title, ID, and TODO status. It is clearly distinguishable from sibling list_elements (which lists elements within a map) and from create_map/delete_elements, so an agent can route correctly 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?

Explicitly says to call this first to resolve existing maps and their IDs before passing mapId to other tools, and mandates re-calling whenever the user asks about state rather than relying on memory. It also states the write restriction when the caller's role on a shared map is 'viewer'.

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 two important behaviors beyond the schema: the moved element's descendants travel with it, and moves are confined to the same map. It says nothing about permissions, what happens to the subtree's internal ordering, or failure conditions for invalid parent/after IDs, leaving meaningful gaps.

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

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

Two tight sentences with the core action front-loaded and zero filler. The second sentence adds genuine value by enumerating the two supported move types. Slightly more could be trimmed or reordered, but it is efficient and well-structured.

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

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

For a hierarchy-mutating tool with no annotations and no output schema, the description covers the essential semantics (subtree moves, same-map restriction, both move kinds) but omits error behavior, idempotency, and any post-move effect. The schema handles parameter detail, so this is adequate but not fully complete.

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 all four parameters (mapId, elementId, newParentElementId, afterElementId) are already documented in the schema, including the null-for-top-level and null-for-first-position semantics. The description adds no parameter-level detail beyond that, so the 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 (move) and resource (one element) with clear scope: within the same map, and the moved element carries its subtree with it. It also clarifies that both cross-hierarchy moves (promote/demote) and same-level reordering are covered, which meaningfully separates it from edit_element and delete_elements. It stops short of naming a sibling explicitly, so it lands at a strong 4 rather than 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?

The phrase 「これ1つで行える」 implicitly tells the agent this single tool covers both reordering and hierarchy changes, which is useful context for tool selection. However, there is no explicit when-to-use vs when-not, no named alternative, and no stated prerequisite (e.g., that IDs must come from list_elements). Usage is implied rather than directed.

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, and it discloses the single most non-obvious behavior: the tool does NOT reproduce the app's parent-check-cascades-to-children display behavior, only the specified elements are written. It omits error/permission/return behavior, but the key semantic trap is covered.

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, all purposeful, with the purpose front-loaded. The cascade clarification and its remedy are a little repetitive but each earns its place by preventing a specific misuse.

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?

No output schema or annotations, but for a simple mutation tool the description covers what is mutated, the scope (single vs batch), and the key filtering/behavioral constraint. Missing only failure and permission semantics, which are minor here.

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 50% (the top-level 'updates' array lacks a description), but the prose compensates by explaining that 'updates' is the enumeration of target elements and that all desired elements must be listed. Combined with mapId/elementId descriptions referencing list_maps/list_elements, an agent can call it correctly.

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: rewriting the checked state of elements in a TODO map, and explicitly notes it handles one or many elements. It does not name a sibling tool (e.g. edit_element) to differentiate, but the scope statement is unambiguous.

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

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

Gives clear operating context: use it when you want to change check state, and if you want children aligned you must enumerate every target element in 'updates'. It does not compare against alternatives like edit_element, but the cascade caveat is a real usage rule.

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