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

With no annotations, the description carries the burden of disclosing behavior. It does so by referring to the inbox as 'the source of truth' and specifying 'open action item,' indicating a write operation to a canonical store. However, it does not mention side effects, permissions, or reversibility, leaving some aspects implicit.

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 followed by clear usage guidance. Every word earns its place, with no redundancy 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?

Given the tool's simplicity (single parameter, no annotations), the description covers purpose and usage effectively. The presence of an output schema handles return values, and the usage guidance compensates for the lack of parameter specifics. Minor gaps remain regarding error cases or integration with other tools, but overall it is sufficiently 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?

The schema has 0% description coverage for the 'text' parameter, and the description does not explicitly explain its format or content. However, the phrase 'Add an open action item' strongly implies that 'text' is the action item's text, providing minimal semantic value 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 clearly states the tool adds an open action item to the vault inbox, naming the resource and specifying the object ('open action item'). It distinguishes itself from sibling tools by focusing on action items rather than notes, making its 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 explicitly says 'Use for tasks/follow-ups, not ideas or status,' providing both positive and negative usage cases. This helps the agent choose this tool over alternatives like create_note or append_daily.

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 burden of behavioral disclosure. It adds 'timestamped' and 'today's journal Log', but omits details like whether the log is auto-created, idempotency, or permission needs. Given the tool's simplicity, this is adequate but not comprehensive.

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, front-loaded sentence with no wasted words. It clearly communicates the action, target, and content scope in a compact form.

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 append tool with an output schema available, the description covers core behavior and usage context adequately. It doesn't address edge cases like missing log creation, but it's sufficient 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?

The schema only provides a type 'string' for 'text', while the description gives the parameter semantic meaning by listing suitable content (decisions, conclusions, etc.) and implying automatic timestamping. This compensates well for the 0% schema coverage.

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 'Append' plus a clear resource 'today's journal Log', and specifies content types (decisions, conclusions, etc.). This distinguishes it from sibling tools like create_note or edit_note which target general notes rather than a daily log.

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 conveys when to use the tool ('as they happen' for decisions/conclusions/work) which is clear context. However, it does not explicitly state when not to use it or mention alternatives, so it falls short of a full 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?

With no annotations, the description carries the full burden and does well. It discloses atomicity (one idea per note), template frontmatter enforcement, and the failure condition on duplicates. It also mentions the wiki-link convention for related notes, making the expected behavior clear.

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, all valuable and front-loaded with the primary action. No filler, and the structure flows logically from purpose to usage to failure behavior.

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 purpose, usage, failure, and linking convention, which is solid for a create tool. However, it omits details about tags/source and the exact frontmatter template, leaving some spec ambiguity that could matter for a note-taking tool with a template.

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. It adds meaning around content (wiki-links) and frontmatter enforcement, but does not explain the 'tags' or 'source' parameters, which are left to names alone. This partially compensates but not fully.

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 creates an atomic idea note in a specific directory, with a specific verb and resource. It distinguishes the creation operation from sibling modification tools (edit, update, rename) by emphasizing the 'create' semantics and the constraint that it fails if a note exists.

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

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

The description explicitly says to use it for durable ideas/insights, advises searching first to avoid duplicates (thereby pointing to the search tool as an alternative), and notes that it fails if the note already exists, implying that edit/update are for existing notes.

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 uniqueness constraint ('old_text must occur exactly once'), the safety property ('cannot drop text you did not quote'), and workspace scope. However, it does not mention error handling (e.g., if old_text is missing) or whether the operation is reversible.

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: exactly four sentences. It front-loads the core purpose, then provides actionable usage guidance. No filler or redundancy; every sentence earns its place.

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

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

For a mutation tool with no annotations, the description covers key use cases: how to invoke correctly (read_note first, ensure uniqueness), when to prefer it over update_note, and its safety property. Since an output schema exists (per context signals), return values need not be described. Minor gaps remain (e.g., error behavior, case sensitivity), but the description is largely sufficient.

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. It explicitly explains old_text ('must occur exactly once', 'copy the passage verbatim') and indirectly implies new_text as replacement. It does not explain name_or_path, but the term is self-explanatory. Overall, it adds meaning to old_text and gives usage tips, but not exhaustive coverage of all 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 starts with a specific verb+resource: 'Surgically correct an existing note by exact string replacement.' This clearly distinguishes it from sibling update_note by emphasizing exact string replacement. It also notes it works anywhere in the file, including frontmatter, further clarifying scope.

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 directs users to read_note first and copy the passage verbatim, adding surrounding lines if not unique. It also states 'Prefer this over update_note for corrections: it cannot drop text you did not quote,' providing a clear alternative and rationale.

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 full burden. It discloses the read-only nature, DuckDB dialect, restriction to SELECT/WITH, and importantly notes the index is rebuilt from files and is never a source of truth. It also warns against selecting 'body' with '*', adding safety-relevant behavioral detail. This goes well beyond minimal disclosure.

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

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

The description is front-loaded with the core purpose, then provides a compact schema and four illustrative examples. Every sentence adds value: the schema clarifies available columns, and examples show realistic queries. It is long but not wasteful, efficiently structured with clear sections.

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 complexity (SQL dialect, custom schema), the description is remarkably thorough. It includes the table schemas, query constraints, examples, and a caveat about data freshness. An output schema exists, so return-value documentation is not needed. No significant gaps remain for an agent to invoke the tool 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 0%, so the description must compensate. It provides multiple SQL examples that implicitly demonstrate the 'sql' parameter usage, but the 'limit' parameter is not mentioned at all. The examples give meaningful context for the sql parameter, yet the description falls short of fully compensating for the missing schema descriptions, especially for limit.

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 'Run read-only SQL (DuckDB dialect; SELECT/WITH only) over the vault metadata index,' which clearly identifies the tool as a SQL query interface for vault metadata. This verb+resource+scope formulation distinguishes it from siblings like search (natural language) and read_note (single note retrieval).

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 states the tool is read-only and works specifically over the metadata index, implying usage for analytical queries rather than full-text or note retrieval. It does not explicitly name alternatives or exclusions, but the context is clear enough that an agent can infer when to use it. Lacks explicit 'use instead' guidance for siblings.

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 read-only nature and the return value (resolved path and full content), but it does not mention error handling when a note is not found or resolution failures.

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, no filler, front-loaded with the action and resource. Every word contributes useful information, and the format is easy to scan.

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 simple nature of the tool (one parameter, read operation) and the presence of an output schema, the description is complete enough. It explains how to specify the note and what is returned, leaving no critical 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?

The schema provides only a bare string parameter with no description. The description compensates fully by explaining the parameter can be a wiki-link name or vault-relative path and gives concrete examples, adding meaning 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 clearly states the tool reads a note by wiki-link name or vault-relative path, with a specific verb ('Read') and resource ('note'). It distinguishes from siblings like search or edit by specifying exactly how to identify and retrieve a note.

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 for when to use the tool: when you have a note's name or path. It does not explicitly exclude alternatives, but the input format examples make the usage scenario obvious.

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 only states 'most recently modified' (implying sort order) and optional type filtering. It does not clarify return format, pagination, or whether this is a read-only operation.

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

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

The description is a single concise sentence that gets to the point. It is front-loaded with the primary purpose ('Most recently modified notes') and adds the optional filter as a secondary 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 simple list tool with an output schema, the description covers the core functionality, but lacks specifics on type values, limit behavior, and expected response structure. The presence of an output schema mitigates the lack of return documentation, but the parameter semantics remain 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 references the 'type' parameter through 'optionally filtered by type', but does not explain valid type values. The 'limit' parameter is entirely omitted, leaving its purpose and effects unclear. Since schema coverage is 0%, this is insufficient.

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 identifies the tool's function: returning recently modified notes with an optional type filter. It distinguishes this from sibling tools like search, query, and read_note by focusing on recency rather than content search or specific note retrieval.

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 rather than search, query, or related. The description does not mention alternatives, prerequisites, or excluded scenarios.

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 that the tool forces a rebuild and returns note and link counts, but it does not mention side effects such as whether the existing index is replaced entirely, whether the operation is safe during concurrent access, or any permission 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?

The description is two short sentences with no unnecessary words. It front-loads the action and directly states the return value, making it highly concise 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 zero-parameter tool with an output schema, the description fully covers what the tool does and what it returns. It is complete for a simple maintenance operation, though additional context about usage could be included but is not essential 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?

The tool has zero parameters, so the parameter burden is minimal. The description does not need to explain parameter details, and the baseline score of 4 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 ('Force a rebuild') and resource ('metadata index') with a clear source ('files on disk'), distinguishing it from sibling note CRUD and search tools. It unambiguously states the tool's function.

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 disk changes or when the index is stale, but it does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusion criteria or comparative guidance is provided.

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 full responsibility. It discloses the specific set of returned data, including a concrete limit (up to 10 tag-shared notes), which is useful behavioral context. It doesn't mention error handling or side effects, but the read-only nature is implied.

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 sentence that packs all key information into a clear structure, with the core phrase front-loaded followed by a colon-separated list. No redundant 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?

The tool is moderately complex, but the description covers the main output categories and a limit. However, the lack of parameter formatting details and any error behavior makes it slightly incomplete. With an output schema present, return values may be covered elsewhere.

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 has no description for the parameter, and the tool description doesn't explain the expected format of 'name_or_path'. The parameter name itself hints at accepting either a note name or path, but the description doesn't specify ambiguity resolution, extensions, or vault-relative paths, leaving the agent to infer.

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 defines the tool's action ('Graph neighborhood of a note') and enumerates the exact outputs (resolved wiki-links, unresolved targets, backlinks, tag-shared notes). This distinguishes it from sibling tools like read_note or search, 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 description implies usage context: when you need note relationships, not content retrieval. However, it doesn't explicitly name alternatives or exclusion criteria, so it has clear context but lacks explicit when-not guidance.

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

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

With no annotations, the description fully discloses behavior: file naming via slugify, H1 heading update, wiki-link rewriting with alias/heading preservation, failure on existing target name, and return values. These are concrete side effects and constraints an agent needs to know.

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 with no filler. The first sentence states the core purpose, and the following sentences provide essential detail on behavior and return values. Everything 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?

The description covers the action, file behavior, heading updates, link rewriting, collision handling, and key return values. The only minor gap is fully defining the name_or_path parameter format, but the parameter name and context make it understandable. The presence of an output schema reduces the need to document return structure.

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. It thoroughly explains new_title (file becomes slugify(new_title).md and H1 updates), but name_or_path is only implied as the note to rename. It doesn't clarify whether it accepts a title, path, or note ID, leaving a gap for that 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 opens with a specific verb+resource: 'Rename a note to a new title.' It then details the exact behavior (file renamed to slugify(new_title).md, H1 updated, wiki-links rewritten), which fully distinguishes it from siblings like edit_note or update_note.

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 context is unambiguous: this tool is for renaming a note. However, it does not explicitly mention alternatives or exclusionary guidance (e.g., use edit_note for content changes). The clear scope and description of side effects make the usage evident, but explicit differentiation from sibling tools is missing.

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, but it only states the basic function. It does not mention search modes, limitations, or result behavior, though the schema's 'match' parameter description does provide meaningful detail about BM25 vs ripgrep semantics. The description itself adds no behavioral context beyond what is inferable from the schema.

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, clear sentence with no fluff, effectively stating the tool's purpose. It is appropriately concise, though it could be enriched with a bit more context without becoming verbose.

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?

Despite a detailed input schema and output schema, the tool description is minimal and does not provide tool-level context such as when to use it vs siblings or how the search behaves overall. It does not explain return values, but the output schema presumably covers that. Overall, the description is incomplete for guiding an agent on when and why to invoke this tool.

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

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

Schema description coverage is 100%, so all five parameters are already well-documented. The tool description adds no parameter-level meaning beyond the schema, hitting the baseline of 3 for high coverage.

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 action ('Search') and resource ('the vault's markdown files'), conveying the tool's core purpose. It does not explicitly differentiate from sibling tools like 'query' or 'related', but the statement is unambiguous about what it operates on.

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 offers no guidance on when to use this tool versus alternatives. While the 'match' parameter description in the schema provides some usage context (ranked for topical recall, exact for identifiers), the tool description itself does not mention any exclusions, prerequisites, or alternative tool recommendations.

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 explicitly states that the frontmatter is preserved verbatim, while everything below it is replaced with content, and warns to read first to avoid losing data. This clearly reveals the tool's destructive behavior and the safe usage pattern, going beyond simple 'update' phrasing.

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 three sentences long, each earning its place: the main action, a key preservation rule with an alternative, and a usage warning. It is entirely relevant, front-loaded, and contains no filler. This is a model of conciseness.

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 update tool with no annotations, the description covers the core behavior, the main pitfall (data loss), and the alternative tool for different needs. The presence of an output schema means return values don't need explanation. It is complete enough for an agent to select and invoke the tool 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 0%, so the description must compensate for the bare parameter definitions. It adds some meaning for 'content' by specifying that everything below frontmatter is replaced with it, but it doesn't explicitly explain 'name_or_path' beyond what the schema shows. Since the tool is simple and the parameters are inferable, the description partially compensates but leaves some ambiguity.

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's function with a specific verb and resource: 'Rewrite a note's entire body.' It also distinguishes itself from edit_note by explicitly mentioning that frontmatter is preserved and that edit_note should be used for frontmatter changes and targeted corrections. This leaves 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 gives direct guidance on when to use this tool versus alternatives: 'use edit_note to change frontmatter' and 'For targeted corrections use edit_note instead.' It also advises reading the note first and carrying forward any content that should survive, which is practical usage instruction. This fully satisfies the dimension.

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