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

Annotations already indicate non-read-only and non-idempotent behavior. The description adds valuable context beyond the annotations: that existing content is preserved and that password-protected notes cause a clear error. It does not contradict the annotations.

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 with no filler. The core behavior is front-loaded, and the critical caveat ('Never replaces existing content') appears immediately after the verb phrase.

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 append operation, the description covers the core behavior, the non-destructive guarantee, and the main failure edge case. No output schema exists, but the agent has enough 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 100%, so the schema already documents both id and text. The description does not add meaning beyond what the schema provides, placing it at the baseline of 3.

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 ('Append'), a resource ('existing note's body'), and a scope ('plain text') in the first sentence. It also distinguishes itself from sibling update_note by explicitly saying 'Never replaces existing content.'

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: to add text without replacing, which contrasts with update_note. Password-protected failure is also stated. However, it does not explicitly name alternatives or give a concrete 'use X instead' routing, so it falls just short of a 5.

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

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

Annotations already signal that this is a mutating, non-idempotent operation. The description adds useful behavioral detail beyond those hints: each line becomes its own paragraph and the title is rendered as a heading. This tells the agent how content will be transformed, which is valuable for predicting the tool's effect.

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 concise sentences with no filler. The core operation is front-loaded, and the formatting behavior is stated immediately in the second sentence. Every part of the description 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 simple create operation with three well-documented parameters and no nested objects, the description is largely complete. It covers the essential creation behavior and formatting semantics, and the schema handles parameter defaults. A minor gap is the absence of any statement about return value or behavior when the target folder does not exist, but these are not critical for selecting or invoking the 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 the baseline is 3. The description adds meaning beyond the schema by explaining that the title is rendered as a heading, which is not present in the title parameter description. It also reinforces the body line-to-paragraph behavior, though folder semantics are left entirely to 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 states a specific verb and resource: 'Create a new note from a plain-text body.' It also distinguishes the operation from sibling tools like append_to_note, update_note, and delete_note by emphasizing 'new note' and describing the input format. The line-to-paragraph and title-heading details further clarify what this tool uniquely 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 phrase 'Create a new note' implicitly signals when to use this tool, but the description never explicitly contrasts it with alternatives such as append_to_note for existing notes or update_note for modifying notes. Usage context is implied rather than stated, and there are no explicit when-not-to-use 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?

The annotations already mark destructiveHint=true, but the description adds important nuance: the note moves to Recently Deleted, stays recoverable for 30 days, and is never permanently destroyed. This materially changes how an agent should weigh invoking the 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?

Two tight, front-loaded sentences communicate scope, side effects, recovery behavior, and boundary conditions without wasted words. Every clause 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 one-parameter delete tool, the description covers what it does, how to invoke it, what happens to the data, and what variants do not exist. The lack of an output schema is acceptable here because the behavioral outcome is fully described.

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 the single 'id' parameter fully. The description confirms 'by id' but adds no extra format, source, or lifecycle detail 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?

States a specific action ('Delete one note by id') with a clear resource and scope. The 'no batch or title-based variant' line also distinguishes it from any broader deletion sibling and from note-search/lookup tools.

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 frames usage as deleting a single note by id and gives a negative constraint: there is no batch or title-based variant. This tells an agent when to use this tool and when not to reach for a non-existent alternative.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only safety profile is covered. The description adds meaningful behavior: multiple title matches are reported as candidates rather than silently guessing, and password-protected notes fail with a clear error. This exceeds the annotation baseline and could reach 5, but does not describe any pagination/limitations or the shape of candidate reporting, so a 4 is appropriate.

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 pack a verb+resource statement, the exclusive-or constraint, matching behavior, and failure behavior with no filler. The core action is front-loaded and each 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 simple read tool with readOnlyHint=true, destructiveHint=false, and 100% schema coverage, the description covers the main calling constraints and edge cases (ambiguous titles, protected notes, rendering formats). It does not specify the output structure, but there is no output schema and the description does mention the formats; a 4 is fair, with 5 withheld only because the candidate-reporting format is not described.

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

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

Schema description coverage is 100%, so the baseline is 3. The description compensates by explaining the mutual-exclusion constraint ('Exactly one of id or title must be given'), the case-insensitivity of title matching, and the behavior on ambiguous titles. These add real meaning beyond the schema's field descriptions.

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 and resource — 'Fetch one note by id or by exact title' — and lists the return formats (markdown, plaintext, or raw html). It distinguishes itself from sibling list/search tools by showing it returns a single note identified by id or title.

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 states the selection condition: exactly one of id or title must be given bracket clarity? The description says the title match is case-insensitive and reports candidates instead of guessing when ambiguous; it also names failure on password-protected notes. This guides when and how to use the tool vs. alternatives like list_notes/search_notes, which are referenced by the parameter descriptions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds the global cross-account scoping behavior, but says nothing about response format or ordering, so it adds only modest context beyond the annotations.

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 that states exactly what the tool does with no wasted words.

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

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

For a parameterless read-only listing tool, the description is sufficiently complete: it names the resource, the scope, and the operation. No output schema exists, but the low complexity and sibling context do not require more.

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

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

The tool has zero parameters and schema coverage is 100%, so the schema fully accounts for inputs. Baseline for a zero-parameter tool is 4; the description correctly signals there are no filter options.

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?

Description uses specific verb 'List' with resource 'Notes.app folder' and explicitly scopes to every account. This clearly distinguishes it from sibling tools, which all operate on notes rather than folders.

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

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

The description implies the tool is for obtaining the full set of folders across all accounts, which provides clear context. However, it does not explicitly state when to prefer this tool over siblings or mention any alternatives/exclusions.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds meaningful behavioral details beyond that: notes are sorted by most recent modification, password-protected notes are skipped, and the limit defaults to 50. These are useful execution-relevant traits not present in the annotations.

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 deliver the core function, ordering, filtering, access behavior, and limit policy. Every sentence earns its place, and the most important behavior is front-loaded.

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

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

The tool is simple, read-only, and has complete schema coverage, so the description covers the essential invocation details. However, there is no output schema and the description does not state what the returned notes contain (metadata vs full content), nor does it explicitly say that omitting folder lists all folders. A little more return-value context would make it 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 the schema already documents folder and limit fully. The description repeats that limit defaults to 50 and max is 200, and that folder restricts results, but adds no meaning beyond the existing parameter descriptions. 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 states a specific action and resource: 'List notes, most recently modified first.' It also clarifies scope with optional folder restriction. It does not explicitly distinguish itself from sibling search_notes, but the verb 'list' plus the ordering 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?

The description gives no guidance about when to use this tool versus search_notes, get_note, or list_folders. The only usage-related hint is 'Optionally restrict to one folder,' which implies use cases but does not name alternatives or exclusions explicitly.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral details: case-insensitive matching, plaintext-body search, skipping password-protected notes, and the default/max limit. Return format and pagination are not mentioned, but the tool is a simple search 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 two compact sentences with no filler. Key information is front-loaded, and every sentence contributes: search scope, matching behavior, exclusions, and limit defaults.

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 low-complexity tool with only two parameters, a complete input schema, and annotations covering the read-only safety profile, this description is sufficient. An agent can correctly invoke it knowing what it searches, what it skips, and how the limit behaves.

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. The description adds semantic value beyond the schema by specifying that matching is case-insensitive and limited to plaintext bodies, which clarifies how the query parameter behaves.

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 ('search') and resource ('notes'), and further narrows scope to 'title and plaintext body'. This clearly differentiates it from siblings like list_notes (listing) and get_note (retrieving a single 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 makes the use case clear: case-insensitive text search across titles and bodies, with password-protected notes skipped. It does not explicitly name alternatives like list_notes or get_note or state when not to use it, so it stops short of full routing guidance.

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

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

The description goes well beyond the annotations by disclosing that the previous body is returned as undo material and that the tool fails with a clear error for password-protected notes. These are important behavioral details not available from the annotations alone.

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 of dense, useful information with no filler. It front-loads the core behavior, then adds the key sibling distinction, return value, and failure mode. 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?

Given the tool's moderate complexity, the description covers all essential aspects: what is overwritten, what is returned, the failure condition, and how it differs from a closely related sibling. No output schema exists, but the description still communicates the key return behavior.

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

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

The input schema already fully documents all three parameters with descriptions, including the optionality of title and the plain-text nature of body. The description reinforces that body is replaced and title is optional but does not add significant semantic detail 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 uses a specific verb ('Replace') and resource ('an existing note's body, and optionally its title'), making the tool's function immediately clear. It also explicitly distinguishes itself from the sibling append_to_note by stating that this tool overwrites content rather than appends.

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 names the alternative append_to_note and explains the key difference: update_note overwrites existing content while append_to_note presumably adds to it. This gives an agent a clear decision rule for selecting between the two tools.

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