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

With no annotations provided, the description carries the full burden. It discloses meaningful non-obvious behavior: per-file locking and optimistic-concurrency checking on expected_hash. However, it does not explain failure behavior when the hash mismatches or what the response looks like, so it is not fully transparent.

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, dense sentence that front-loads the action and adds the concurrency caveat without any filler. Every word contributes useful information.

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?

This is a mutation tool with no annotations and no output schema. The description omits error behavior, lock semantics in practice, whether the note must pre-exist, and how optimistic-concurrency failures surface. That makes it incomplete for safe 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?

Schema description coverage is 0%, so the description must compensate. It only clarifies expected_hash's role in the concurrency check, while note and content are left to name inference. It does not explain how to obtain or format expected_hash, which is critical for correct invocation.

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 ('Append to a note') and the resource, which distinguishes it from read/list/move/search operations. It does not explicitly name sibling alternatives, but the verb 'append' makes the core 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?

No guidance is provided about when to use this tool versus alternatives like create_inbox_note or update_metadata. It also does not state prerequisites such as whether the note must already exist or how to obtain the expected_hash.

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. It reveals batch behavior ('entries'), destination ('review area'), and safety/recovery mechanics ('batch rollback manifest', 'Run dry_run first'). It doesn't specify whether original notes are removed or how the manifest is consumed, but the key behavioral traits are present.

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

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

Two short sentences, front-loaded with the action then the mandatory safety step; no filler.

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

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

Given no output schema and no annotations, an agent lacks the return shape, the exact effect on original notes, and how the rollback manifest is used. The dry-run and manifest notes prevent this from being inadequate, but there are meaningful gaps for a batch mutating 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?

Schema coverage is 0% and entries is an opaque object array, so the description's '(note, hash, category)' is the only definition of entries content. It also gives dry_run a purpose. It stops short of specifying required keys or value formats, but it compensates substantially for an empty 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?

States the verb 'Archive', the resource 'notes', and the destination 'review area'; the tuple '(note, hash, category)' defines scope. It is distinct in meaning from move_note, list_archives, and restore_archive, but it does not explicitly name an alternative to prevent confusion.

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 a clear operational instruction: 'Run dry_run first.' It does not say when to choose archive_notes over move_note or other siblings, nor when not to use it. Selection context must be inferred from the word 'archive'.

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 carries the full behavioral burden because no annotations are provided. It discloses the important non-overwrite guarantee, but does not explain what happens on a filename collision (error, no-op, rename), or whether permissions or directory creation are required. This is partial transparency.

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?

A single concise sentence with the operation and scope front-loaded. The non-overwrite safety warning earns its place as critical behavioral information. No filler.

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

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

For a three-required-parameter create tool with no output schema, the description covers the core action and folder enumeration but omits conflict handling behavior and content/filename expectations. Since the 'never overwrites' statement immediately raises the collision question, some explicit error/return behavior 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?

Schema has no descriptions for the three required parameters (0% coverage), so the description must compensate. It adds useful semantics for the folder parameter by limiting values to Web/Conversations/Files, but content and filename are left to inference from the parameter names. No format or constraints are provided.

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 ('Create') and resource ('a note') with the location ('inbox directory') and enumerates the possible directories (Web/Conversations/Files). This clearly separates it from sibling tools that read, list, move, search, append, update, or archive 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?

Does not name alternative tools or give explicit when-to-use versus when-not-to conditions. The clause 'Never overwrites an existing file' implies it is for new notes rather than modifying existing ones, but doesn't explicitly route to append_note, move_note, or other 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?

There are no annotations, so the description carries the transparency burden. 'List' implies a read-only operation and 'with their restore accounting' hints at the returned data, but the description does not disclose pagination, ordering, or response details.

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 with the verb and resource front-loaded. There is no filler or redundant restatement.

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 is adequate for a simple list operation, but it leaves 'archive batches' and 'restore accounting' undefined and does not mention the limit parameter. With no output schema, this leaves some gaps around expected 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 0% and the description never mentions the 'limit' parameter. While the name and default value hint at a page size, the description adds no semantic value beyond what the schema already shows.

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

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

The description uses a specific verb ('List') and resource ('archive batches'), and adds that they are returned with their restore accounting. This makes the primary action clear and distinguishes it from list_notes at the resource level, though it does not explicitly name sibling alternatives.

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

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

No explicit when-to-use or when-not-to-use guidance is given. The resource name implies the tool is for listing archive batches and their restore accounting, but the agent must infer this usage context rather than being told directly.

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 transparency burden. It does add useful behavioral facts—private notes are omitted and ordering is newest-first—but it does not disclose side effects, pagination behavior, or whether returned paths are absolute or relative.

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?

A single, compact sentence front-loads the core operation and packs in the important qualifiers: private exclusion, ordering, and filter types. There is 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 list operation, the description is largely sufficient: it states the output (note paths), the scope (private excluded), the order (newest first), and available filters. The missing limit semantics and exact return format are minor given the tool's simplicity.

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%, but the description partially compensates by interpreting folder as a prefix and pattern as a substring. The limit parameter is left unexplained, so the agent must rely on the name and default value.

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 operation ('List note paths') and adds scope qualifiers: private notes are excluded and results are newest-first. This clearly distinguishes the tool from siblings like read_note (single-note retrieval) and search_notes (content search).

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 the tool's purpose evident, but it never explicitly states when to prefer list_notes over search_notes or rag_search. No alternatives or exclusions are named, so the agent must infer routing from the sibling names.

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 of behavioral disclosure. It does disclose two important constraints: moving into private areas is forbidden and the destination must not already exist. However, it does not describe side effects such as whether old paths are invalidated, error behavior, or reversibility, leaving the mutation behavior only partially transparent.

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 efficient sentence that front-loads the core action ('Move a note within the vault') and then appends the two essential constraints. There is no filler or redundant restatement of the tool name.

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 mutating tool with no annotations and no output schema, the description omits key context: what a successful move returns, what happens if the source note does not exist or the destination already exists, and how expected_hash interacts with the move. The two constraints are helpful but not enough for confident 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?

Schema description coverage is 0%, so the description must compensate, but it only clarifies the destination parameter ('destination must not exist,' 'never private'). It adds nothing about 'note' or 'expected_hash'; the optional hash parameter is entirely unexplained. Thus the description only partially compensates for the schema's lack of parameter documentation.

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 and resource, 'Move a note within the vault,' which is unambiguous and immediately distinguishes this from the listed siblings such as append_note or archive_notes. The added constraint 'never into a private area' further refines the operation. No other sibling tool performs a move, so the purpose is fully clear.

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 use when relocating a note inside the vault, but it does not state when to prefer this over alternatives or call out any when-not-to-use conditions. Constraints like 'destination must not exist' act as preconditions, not usage guidance. There is no explicit reference to alternatives among sibling 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 provided, the description carries the full burden of behavioral disclosure. It does not state whether re-indexing is destructive, whether it requires special permissions, how long it takes, whether it blocks other operations, or what the output/return value is. 'Incrementally' hints at non-destructive behavior but is not explicit.

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 with no wasted words, and the key action is front-loaded. However, it is so terse that it sacrifices useful context; it is concise but under-specified.

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

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

For a tool with one parameter, no annotations, and no output schema, the description should explain the parameter's effect, the operation's side effects, and the expected result. It does none of these. The sibling context (rag_search, rag_status) suggests this is part of a RAG pipeline, but the description does not connect to that workflow.

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 undocumented 'force' parameter. It does not explain what 'force' does, when it should be true, or the difference between incremental and forced re-indexing. The description adds no parameter-level meaning beyond the schema's bare boolean type.

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 ('re-index') and resource ('the vault'), and the word 'incrementally' adds some scope. However, it does not distinguish this from sibling tools like rag_search or rag_status, and 'rebuildable derived index' is somewhat jargon-heavy without explaining what the index is used for.

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 given on when to use this tool versus alternatives. The description does not mention prerequisites (e.g., whether the vault must already be indexed), when a force re-index is needed, or how this relates to rag_search or rag_status. An agent would have to infer usage from the name alone.

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

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

No annotations are provided, so the description carries the full burden. It discloses that excerpts are non-authoritative candidates and warns to verify with read_note, which is valuable. But it does not explicitly state whether the operation is read-only, how scores or traceability fields are structured, or any limitations such as pagination or indexing 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 tight sentences with no filler. The first states the core purpose, and the second provides a critical usage warning, so every word 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?

With no annotations, no output schema, and zero schema description coverage, the description leaves too many gaps. An agent still lacks clarity on parameter meaning, return structure, and how this tool relates to the sibling search_notes, despite the useful excerpt warning.

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%, and the description provides no explanation of query, limit, or paths semantics. An agent sees only parameter names and defaults, with no guidance on expected values or behavior.

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

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

The description states the tool performs retrieval with per-note scores and mentions note-related output, making the core purpose reasonably clear. However, it does not distinguish rag_search from the sibling search_notes tool, so an agent may not know when to choose one over the other.

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 a clear post-retrieval instruction: excerpts are candidates, so call read_note before citing. This is useful, but there is no guidance on when to use rag_search versus search_notes or when not to use this tool.

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

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

With no annotations, the description carries the full burden. It does disclose a key behavioral guarantee (no note contents are exposed) and implies a read-only status check, but it does not explicitly state side-effect-freeness, data freshness, or whether the metadata is cheap or expensive to compute.

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

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

One sentence, front-loaded with the core function, followed by the most important privacy caveat. Every word 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 parameterless status tool, the description covers what it returns and what it deliberately omits. It is slightly thin on output format and error/edge behavior (e.g., empty or missing index), but the low complexity makes this a minor gap.

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

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

The tool has zero parameters, so the 0-param baseline applies. The description consequently has no parameter meanings to add; the empty schema is sufficient.

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

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

The description identifies the exact resource (index health metadata), lists concrete examples (document/chunk counts, schema version), and contrasts itself with note contents, clearly distinguishing it from read_note, search_notes, and rag_search. The purpose is unmistakable.

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 given for when to call this tool versus rag_reindex or rag_search. The word 'health' implies diagnostics, but there are no stated conditions, exclusions, or alternative 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?

No annotations are provided, so the description carries the behavioral disclosure burden. It meaningfully reveals that private notes are never readable and that the tool returns the full-content hash, not raw note text. It does not cover error behavior, authentication, or how offset/max_length shape the response, but the core access and return semantics 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 two short sentences with the main action front-loaded. Every clause adds value — operation, addressing, return type, and a key restriction — with no redundancy or filler.

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

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

The description covers the core read operation, path-based addressing, the private-note restriction, and the return type. However, with no output schema and no annotations, it omits the semantics of offset/max_length, behavior for missing or inaccessible notes, and what distinguishes a 'standard note' from other note types, leaving it minimally complete for a three-parameter 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 0%, so the description must compensate for the bare parameter titles. It clarifies only the `note` parameter as a vault-relative path and hints at the output being a hash. The `offset` and `max_length` parameters are left entirely unexplained beyond their names and defaults, which is a significant gap.

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 operation ('Read'), the resource ('a standard note'), and the addressing mechanism ('vault-relative path'). It also adds a key distinction — private notes are never readable — but it does not explicitly name or contrast sibling tools like search_notes or list_notes, so the differentiation from alternatives is not fully explicit.

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 you have a known vault-relative path and need to read a standard note. It also states an exclusion ('Private notes are never readable'), but it gives no explicit guidance about when to prefer read_note over list_notes, search_notes, or rag_search, nor any alternative tool for private 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 behavioral burden and does add useful context by listing skipped cases: already-restored, missing, altered, or occupied entries. However, it omits other behavioral details such as return value, failure handling, permissions, and whether the archive entry is removed after a successful restore.

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?

A single front-loaded sentence states the primary operation first and then lists the exception cases compactly. There is no filler, repetition, 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 tool with no output schema and no annotations, the description is too sparse: it does not explain what 'only' or 'dry_run' do, what the default 'latest' batch means, or what the result of the operation looks like. The skip behavior is a good start, but important call-time context 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?

Schema description coverage is 0%, and the description provides no meaning for the three parameters: only, dry_run, and batch_id. It only uses the word 'batch' generically, which does not clarify defaults or semantics, so the description fails to compensate for the schema gap.

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 and resource: 'Restore an archived batch back to its original paths.' It distinguishes the tool from siblings like archive_notes and list_archives by describing the reverse operation, so an agent can identify when restore_archive is applicable.

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 use case is implied: call this when an archived batch needs to be returned to its original paths. However, it does not explicitly state when not to use it, name alternatives among the sibling tools, or mention prerequisites such as requiring an existing archive.

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 goes beyond a simple restatement by revealing the execution strategy (index search) and the fallback to a linear vault scan when the index is empty, which is valuable operational behavior. It does not mention read-only status, but 'search' reasonably implies non-mutating behavior, and no side effects are relevant for this 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 description is a single, front-loaded sentence with no filler. It packs the core purpose and a key behavioral nuance into the smallest possible space, earning every word.

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

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

For a tool with three parameters, no parameter descriptions in the schema, no annotations, and no output schema, the description is too sparse. It omits any explanation of what 'paths' controls, how 'limit' behaves, or what the result shape is. The fallback detail is nice, but it does not fill the major gaps an agent needs to call 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 lack of parameter documentation. It only implies the 'query' parameter through 'keyword search' and leaves 'limit' and 'paths' completely unexplained. Without additional parameter context, an agent cannot infer how to scope or paginate results.

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-resource pair ('Keyword search over indexed notes') and distinguishes itself from the sibling rag_search by explicitly labeling the search as keyword-based. The fallback behavior is an additional specific detail that further clarifies 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?

Usage context is implied by the phrase 'keyword search' — it signals when to prefer this tool over a semantic search tool like rag_search — but there is no explicit when-to-use/when-not-to-use guidance or mention of alternatives. The fallback text hints at behavior, not usage conditions.

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 of behavioral disclosure. It explicitly states a destructive side effect: 'other keys are dropped,' meaning any keys not in the allowlist will be discarded. This is valuable beyond simply saying 'Update.' However, it does not mention behavior around expected_hash, permissions, or reversibility, but the dropping detail is the most critical.

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 filler. Every phrase carries information: 'allowlisted set' scopes the operation, enumerates example fields, and the final clause discloses the destructive behavior. There is zero 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 3-parameter mutation tool with no annotations and no output schema, the description is too sparse. It does not clarify what 'note' refers to (ID, path, content), the purpose or format of 'expected_hash,' or the exact semantics of the allowlisting (e.g., are existing allowlisted fields preserved if absent from 'fields'?). An agent would need to make assumptions to call this 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 some semantics for the 'fields' parameter by listing example allowlisted keys (status/tags/agent_generated) and noting non-allowlisted keys are dropped. But it does not explain the 'note' parameter or the 'expected_hash' parameter (likely a concurrency guard), leaving the agent to guess their meaning and use.

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 ('Update') and resource ('frontmatter fields'), and clarifies the scope with 'allowlisted set' and 'other keys are dropped.' This clearly distinguishes it from siblings like move_note, append_note, or archive_notes, which operate on different aspects of 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 does not provide any guidance on when to use this tool versus alternatives, does not mention prerequisites, and offers no explicit exclusions or alternative tool names. It only states what the tool does, leaving the agent to infer when it is appropriate.

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