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

Beyond readOnlyHint=true, it discloses the required runtime state (app open, agent connection active) and that the tool reports when that condition is unmet, which is genuine behavioral context an agent needs. It doesn't cover freshness/caching behavior, so not quite a 5.

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

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

Content is front-loaded: what the tool returns first, then when to call it, then the precondition. The enumeration is dense but each clause carries information; slightly long for a no-argument tool.

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

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

There is no output schema, so the description must describe the returned payload, and it does so field by field (path, mode, heading path, line range, selection, unsaved edits). Combined with the stated precondition, an agent has everything needed to call and interpret it.

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

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

The tool takes zero parameters, so there is nothing for the description to clarify beyond the baseline. The enumeration of returned fields adds value but is not parameter semantics.

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 resource (the person's current TrailMark context) and enumerates exactly what that includes: open document, read/edit mode, on-screen section, selection, and dirty state. This is far more specific than the sibling list_* tools and immediately distinguishes it.

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

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

It gives explicit trigger conditions with quoted user phrasings ("this", "here", "the selected text", "this section") and states the prerequisite (TrailMark open with agent connection on). No alternative sibling is named as a fallback, so it stops 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 only cover readOnlyHint, and the description adds substantial context beyond them: the meaning of each `state` value (anchored/passageChanged/documentGone) and what the line number means in each case, the `warning` field explaining an empty list, and the fact it works with TrailMark closed.

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?

Dense but front-loaded with the resource and its fields, then state semantics, then usage trigger, then the warning caveat. Slightly list-like in enumerating output fields, but with no output schema that content 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 output schema, the description fully documents the returned fields and the meaning of the state enum, plus failure behavior and offline operation. An agent has everything needed to call and interpret this 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 100% and the schema text for `which` ('open (the default), done or all') is essentially identical to the description's restatement. Baseline 3 is appropriate since the schema already carries the parameter semantics and the description adds no new syntax or format detail.

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

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

States a specific verb+resource (comments the person left) with precise scope: passages of the project's Markdown documents, illustrated with example quotes. It is immediately distinguishable from siblings like list_notes, list_tags, and resolve_comment.

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 triggering condition ('Call this when the person asks you to go through, address or apply their comments') and explains the default filter plus how to change it via `which`. It does not explicitly name the alternative (resolve_comment) or state when not to use this tool, so 4 rather than 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 declare readOnlyHint=true, so safety is covered; the description adds the sharing/permission model, newest-first ordering, the fact that the notes folder itself cannot be listed, and that it works when TrailMark is closed. It stops short of describing result limits or pagination, so it is not exhaustive.

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?

Front-loaded with the resource and the returned fields, then the trigger, then the constraints. The parenthetical explaining the Notes window is slightly digressive but still carries real information about scope and privacy.

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

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

With no output schema, the description carries the burden of return-value semantics and does so, naming the fields and ordering. It also covers the privacy boundary and offline behavior, so an agent has everything needed to call and interpret it.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The description's field notes (`note`, `title`, last-changed, size) describe the returned records rather than inputs.

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

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

Uses a specific verb+resource (list the shared notes in TrailMark) and immediately differentiates from the sibling read_note by naming the `note` field read_note consumes. An agent can tell it apart from list_comments, list_tags, and list_unread without opening a schema.

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

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

Gives an explicit trigger with representative user utterances ("my note about the deploy", "the prompt I wrote", "what I jotted down") and states the negative case: a note that is not shared is not listed and cannot be read, routing the agent to read_note only for shared 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?

readOnlyHint already declares this a safe read, but the description adds context the annotation does not: origins of tags (frontMatter vs trailmark vs both), default page sizes (first 50), truncation signaling (`more`), and operation when TrailMark is closed. It does not contradict the read-only annotation; the only gap is lack of explicit statement that no mutation occurs (already covered by 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?

Front-loaded with the core purpose, and each sentence carries information (fields, origins, defaults, workflow). It is dense and reads as an unbroken block rather than being split into scannable units, and the parenthetical detail borders on over-specification, but there is little genuine waste.

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

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

With no output schema, the description compensates by documenting the return shape in detail (count, from, documents, untagged, more/total) plus the alternate mode's fields. For a 2-optional-param read-only tool this is fully sufficient to call it 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: `tag` is not just a filter but switches the entire output shape from tags to documents, and `limit` interacts with two different default/cap regimes (50/200 tags vs 20/100 documents). That framing exceeds the schema's field-level description.

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

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

States a specific verb and resource ('list_tags' returning tags in the project's Markdown documents) and enumerates the exact payload fields (count, from, documents, untagged, more). It also defines a second mode (passing `tag` lists documents instead), so an agent can distinguish behavior from siblings like search without opening a schema.

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

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

Explicitly prescribes a workflow ('find the right documents in two calls'), names the alternative ('or search with `tags`') and the condition that selects it, and notes a special case ('also works when TrailMark is closed'). When-to-use and alternatives are both spelled out.

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

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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds real value beyond that by disclosing ordering (newest change first), that each item carries the change time, and that it works even when TrailMark is closed by reading from the project's files. It does not describe volume, pagination, or per-person scoping.

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, front-loaded with what is returned before the when-to-use guidance. Every clause earns its place, with only minor redundancy in the parenthetical example.

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 parameters, no output schema, and readOnlyHint covering the safety profile, the description supplies enough for correct invocation: what it returns, ordering, timing, and the closed-app fallback. It could be more complete by noting the response shape or any limits, but nothing essential is missing.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. The description correctly implies the scope is implicit (the current person's read state) rather than configurable.

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 resource and scope: 'The Markdown documents that changed since the person last read them in TrailMark,' which is clearly distinct from siblings like search, read_note, and list_notes. It is precise about what is returned and in what order, though it never explicitly names a sibling to differentiate from.

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

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

Gives explicit trigger conditions: 'when the person asks what changed, what they have not read yet, or to catch up,' plus a concrete example (after an agent edited documents). No when-not guidance or named alternative (e.g., search) is offered, so it stops 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?

Adds real behavioral context beyond the annotations: it does not steal terminal focus, it highlights the section, shows a notice with a way back, and launches TrailMark if the project is closed. The stated 'never changes a document' guarantee is consistent with readOnlyHint=false, which reflects side effects on app state (window/app launch) rather than document mutation.

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?

Purpose is front-loaded in the first clause, and each sentence adds something (trigger, side effects, non-mutation guarantee). It is somewhat clause-heavy in the middle sentence, which slightly dilutes scanning, but there is 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?

With three parameters, no output schema, and minimal annotations, the description carries and covers the key behavior an agent needs. It omits edge cases such as what happens when the path or heading does not exist, which is the main residual 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?

Schema description coverage is 100%, so path, line, and heading are already fully documented, including the rule that heading wins over line. The description only restates 'optionally at a line or a heading' and adds no format, range, or fallback detail, so baseline 3 applies.

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

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

Specific verb plus resource ('Show the person a place in TrailMark: a document, optionally at a line or a heading') and a scope boundary ('It only shows; it never changes a document'). This clearly distinguishes it from the read/list siblings such as read_note, search, and list_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?

Gives a concrete trigger: 'Use it after you wrote or found something they should see' with an example invocation phrase. It stops short of naming alternatives or exclusion cases (e.g. when to prefer read_note or search instead), so it falls just below the top band.

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?

Beyond the readOnlyHint annotation the description discloses useful behavior: it cannot modify anything, non-shared notes are reported as non-existent (a deliberate hiding behavior an agent must expect), and it works even when TrailMark is closed. This goes well past the structured safety hint.

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 short sentences, front-loaded with what is read and what comes back, then the two behavioral caveats. No filler and nothing repeated from the schema.

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 a single documented parameter, no output schema, and a readOnly annotation, the description covers everything an agent needs: the return shape (title and whole text), the error semantics for unshared notes, and availability when the app is closed.

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% and the schema already explains the exact `note` name format with an example. The description's mention of the note name and its source in `list_notes` reinforces but does not add meaning beyond the schema, so the baseline 3 applies.

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

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

States a specific verb (read) and resource (one shared note) and pins the input to the `note` name produced by `list_notes`. It explicitly distinguishes itself from the sibling `list_notes` by operating on a single note rather than the list, and it names the return payload (title + whole text).

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 tells the agent where the `note` argument comes from (`list_notes`), which is the key routing prerequisite. It does not state an explicit when-not or contrast against `search` or `get_context`, so it stops short of full alternative 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?

Annotations already flag this as a non-destructive write, but the description adds real behavioral context beyond them: the optional reply is surfaced under the comment for the reader, and the tool works even when TrailMark is closed, operating directly on the project's files.

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

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

Three sentences, front-loaded with the action and its trigger, with no filler. It is slightly dense because it folds the reply rendering, id source, and write-scope limit into one sentence, but 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?

No output schema exists, but the description covers what changes, where the id comes from, and the side effect on the reader, which is enough to invoke it correctly. It omits edge cases such as invalid or already-resolved ids, 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?

Schema description coverage is 100%, so both `id` and `reply` are already documented in the schema, including the 'Rewritten in 3f2a1c' example. The description restates the same information without adding format or constraint details, so the baseline 3 applies.

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

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

The description states a precise verb+resource ('Mark one comment done') and scopes it with the condition 'after you addressed it'. It is immediately distinguishable from read-only siblings like list_comments and list_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?

It names the trigger ('after you addressed it'), the prerequisite for obtaining the argument ('Use the `id` from list_comments'), and an explicit boundary ('it cannot write comments or edit documents'), which routes the agent correctly among 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?

With readOnlyHint already declaring the safety profile, the description adds substantial behavior: the exact shape of each result (path, heading path, line, short snippet), the fact that document `tags`/`description` accompany results, the ranked/section-vs-document mode change based on whether `query` is supplied, and the notable fact that it 'also works when TrailMark is closed, from the project's files.'

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?

Front-loaded with purpose and return shape, then usage, then the large-project strategy — a sensible order with little waste. Slightly over-long, and the `query`/`tags` mode rule is restated in the schema, so one sentence is partly redundant.

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

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

No output schema exists, yet the description fully specifies the return payload (ranked sections with path, heading path, line, snippet, plus document tags/description) and the alternate return when `tags` is used without `query`. Nothing an agent needs in order to call and interpret the result 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 coverage is 100%, so the baseline is 3; the description adds genuine semantics beyond the schema by explaining the interaction between `query` and `tags` (omitting `query` converts the call from a section search into a document listing) and by recommending `tags` as the narrowing step in large projects.

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

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

States a specific verb and resource — 'Find where something is described in the project's Markdown documents' — and immediately characterizes the return as ranked matching sections. It further distinguishes itself from siblings by framing the job as locating documentation 'before reading whole files,' positioning it against read_note/open.

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

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

Gives explicit when-to-use ('to locate documentation before reading whole files, for example to find the section that defines a term or a decision'), a concrete narrowing strategy for large projects, and names the sibling `list_tags` as the prerequisite for the tags path. It also states the mode switch: leave `query` out when passing `tags` to list documents instead of sections.

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