Read-only search and Markdown for The Notetakers reviews of AI meeting notetakers.
Scored across 3 tools
Each tool targets a distinct read mode: search_posts for discovery, get_post_markdown for a single post, and get_llms_txt for whole-site or bulk reading. The descriptions explicitly disambiguate boundaries by telling the agent when to use one over the other.
All names use snake_case with a verb_noun structure (get_llms_txt, get_post_markdown, search_posts). get_llms_txt is slightly less conventional since the noun is a filename artifact, but the pattern is still clearly readable and predictable.
Three tools is on the thin side but well-matched to a read-only published-content site, with each tool covering a distinct access granularity (discover, single, bulk). No redundant or filler tools.
The discover-then-read lifecycle is fully covered for a read-only content server, so no create/update/delete is expected. Minor gaps exist around tag/category browsing or pagination for large result sets, but core agent workflows are supported.
Return the site llms.txt index: what the site covers, every post with its Markdown URL, and other agent entry points. With full set to true, return llms-full.txt, which includes every post body. Use for a whole-site overview or bulk reading, not for finding one post; use search_posts for that.
| Name | Required | Description | Default |
|---|---|---|---|
| full | No | Return /llms-full.txt instead of /llms.txt. Defaults to false. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context, which it does by disclosing the return shape and the effect of full=true ('includes every post body'). It does not mention response size, pagination, or caching, which would matter for a bulk-read tool, so it stops short of a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler, with the return contents front-loaded and the routing guidance last. 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?
With no output schema, the description carries the burden of describing the return and does so adequately (index contents, post URLs, full-body variant). A single boolean parameter at 100% schema coverage and a clear sibling distinction leave nothing an agent needs 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 goes beyond the schema's 'Return /llms-full.txt instead of /llms.txt' by explaining what that difference means in practice ('includes every post body'). That added semantic content justifies a bump above baseline.
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 ('Return the site llms.txt index') and enumerates what it contains: site coverage, every post with its Markdown URL, and other agent entry points. It also names the sibling it is not ('not for finding one post; use search_posts for that'), so an agent can distinguish it without opening the 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 explicit when-to-use ('whole-site overview or bulk reading') and when-not ('not for finding one post'), and names the correct alternative tool (search_posts) for that case. Nothing is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the full Markdown of one post, with YAML frontmatter, as served at /.md. Use when you already have a slug from search_posts. To read many posts at once, use get_llms_txt with full set to true instead.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Slug of the post, as returned by search_posts, 1 to 200 characters. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds useful return-format context: full Markdown with YAML frontmatter, served at '/<slug>.md'. It does not discuss error behavior or truncation, but for this simple read-only tool the added context is meaningful.
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-loads the core behavior, and then immediately covers usage and the sibling alternative. Every sentence earns its place with no 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?
For a one-parameter, read-only retrieval tool with no output schema, the description gives enough: what is returned, how it is delivered, when to use it, and which alternative handles many-post retrieval. An agent has what it needs to select and invoke 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 description coverage is 100%, and the single slug parameter is fully documented in the schema. The description reinforces that the slug comes from search_posts, but it does not add syntax or format details beyond the schema, so the baseline score of 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 uses a specific verb and resource: 'Return the full Markdown of one post, with YAML frontmatter.' It also specifies the delivery form via '/<slug>.md' and distinguishes this single-post tool from the many-post sibling get_llms_txt.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says when to use it: 'Use when you already have a slug from search_posts.' It also names the alternative for a different need: 'To read many posts at once, use get_llms_txt with full set to true instead.'
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find or list published posts. Returns slug, title, description, canonical URL, Markdown URL and last updated date for each match, newest updated first, without the post body. Use this first to discover slugs, then call get_post_markdown for the full text. Matches query case-insensitively against title, description and body; omit query to list the newest posts.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of posts to return, 1 to 50. Defaults to 20. | |
| query | No | Case-insensitive text to find in post titles, descriptions and bodies, up to 200 characters. Omit or leave empty to list posts newest first. |
| Name | Required | Description |
|---|---|---|
| posts | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the read-only, idempotent, non-destructive profile, so the description earns credit for adding matching semantics (case-insensitive across title, description and body), ordering (newest updated first), and the explicit exclusion of the post body. It stops short of pagination/truncation behavior, which keeps it from 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?
Three sentences, all front-loaded: what it returns, how to chain it, how matching works. No filler and each sentence carries distinct 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?
Even though an output schema exists (so return values need not be explained), the description usefully previews the returned fields and emphasizes the body is omitted, which prevents a wrong assumption about payload size. Combined with the sibling routing, an agent has everything needed 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 description coverage is 100%, so both parameters are already documented including defaults and bounds. The description restates the query matching semantics and the omit-to-list behavior but adds no syntax or formatting detail beyond the schema, matching the baseline for full-coverage schemas.
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 or list published posts') and scopes it to published posts only. It explicitly contrasts itself with the sibling get_post_markdown, so an agent can distinguish the two 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 workflow: 'Use this first to discover slugs, then call get_post_markdown for the full text,' and states the condition that selects the other mode ('omit query to list the newest posts'). Nothing is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_llms_txtget_post_markdownsearch_postsSearch and read your recorded meetings: notes, action items, participants, transcripts.
Read-only access to your RecordX meetings: search transcripts, summaries, action items.
Personal context for every AI: search, read, and write back to your private Markdown library.
Search meetings, export summaries and transcripts, and manage recordings from any AI tool.
Add one secure layer between your agents and this server.
