Yerevan Product Coffee: table dates, remaining seats, seat requests, and the field notes behind it.
Scored across 6 tools
Each tool has a clearly distinct purpose: three cover field notes at different levels (list, search, get full text), while the others cover sprint information and table seat requests. There is no meaningful overlap or risk of selecting the wrong tool for a task.
All tool names follow the same verb_noun snake_case pattern: get_, list_, search_, request_. The singular/plural noun difference aligns naturally with the tool's function and does not create confusion.
Six tools is a well-scoped size for a personal content-and-offering server. Each tool addresses a distinct user need without redundancy or bloat.
The surface covers the full intended workflows: discovering, searching, and reading field notes; learning about the sprint offering; and checking table availability and requesting a seat. No obvious missing operations or dead ends exist for the stated domain.
The complete text of a single field note. Use this after search_field_notes or list_field_notes, which return only an excerpt. Accepts the slug, the path, or the full URL — 'what-30-days-of-crawler-logs-showed', '/what-30-days-of-crawler-logs-showed' and 'https://hovhannes.io/what-30-days-of-crawler-logs-showed' all work.
| Name | Required | Description | Default |
|---|---|---|---|
| note | Yes | The note's slug, path, or URL |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| text | Yes | The note in full, as plain text |
| title | Yes | |
| category | Yes | |
| readTime | No | |
| publishedAt | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds valuable behavioral context: it clarifies that the tool returns the complete text (as opposed to excerpts) and explains that the input can be a slug, path, or URL with concrete examples. This goes beyond the annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded: first the purpose, then the usage context, then the parameter format. Every sentence contributes. The example list is slightly verbose but serves a clear clarifying purpose for a voice-input‑friendly interface. No fluff.
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‑only tool with one parameter and an output schema present, the description covers the essential aspects: what it returns (complete text), when to use it (after list/search), and what the input can be (slug/path/URL). It does not need to explain return structure because the output schema exists. Nothing important 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 schema has 100% coverage with a clear description for the 'note' parameter ('The note's slug, path, or URL'). The description reinforces this and adds real examples of each format, which is more actionable than the schema alone. It does not introduce ambiguity or conflict.
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 clear verb ('Read') and resource ('one field note') with the qualifier 'in full', and explicitly contrasts it with sibling tools that return only an excerpt. This differentiates it from list_field_notes and search_field_notes without ambiguity.
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 instructs to use this tool after search_field_notes or list_field_notes, which is a clear, usable trigger. It does not explicitly state when not to use it, but the context strongly implies it should not be used for searching or listing since those are covered by siblings. The guidance is strong but not exhaustive on exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What a Clarity Sprint is, what it produces, how long it takes, what it costs, and where to apply. Use this when asked how to work with Hovhannes or what he offers.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| name | Yes | |
| price | Yes | |
| applyAt | Yes | |
| summary | Yes | |
| duration | Yes | |
| guarantee | Yes | |
| deliverable | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes that this is a safe read operation, so the bar for additional disclosure is lower. The description adds useful context about the scope of content (what Clarity Sprint is, costs, deliverables), but it does not mention whether it returns static information versus dynamically pulled data or any limitations. This is adequate, not exceptional.
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 tight sentence that front-loads the tool's content coverage and ends with a direct usage trigger. Every phrase earns its place and there is no filler or repetition of the title or annotations.
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 tool with an output schema, this description is fully sufficient. It names the resource, lists the key return topics, and tells the agent when to use it. No critical invocation guidance 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 has zero parameters, so there is no schema information to compensate for. The description usefully specifies the semantic content of the returned details, which is all the guidance an agent needs for a parameterless call.
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 resource (a Clarity Sprint) and enumerates the exact information returned: definition, deliverables, duration, cost, and application location. It lacks an explicit imperative verb like 'retrieves' or 'returns', but the intent is unambiguous and it is not confusable with the field-note sibling 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?
The description gives a direct usage condition: 'Use this when asked how to work with Hovhannes or what he offers.' This clearly signals the triggering scenario. It does not explicitly exclude alternatives, but the sibling tools are topically distinct enough that no confusion is likely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every published field note with its title, category and date, newest first. Use this to see the full range of what has been written before searching within it, then get_field_note to read one in full.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| notes | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds useful behavioral context: only published field notes are returned, ordering is newest first, and each item includes title, category, and date. It does not mention pagination or result limits, but that gap is minor given the output schema is 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 sentences with no filler: the first states the full scope, ordering, and included fields; the second provides adjacent tool guidance. The key purpose is front-loaded and 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?
The description is complete for a parameterless, read-only list tool: it defines the output fields, ordering, and the workflow for reading a full note. The output schema covers return structure, so no additional return-value detail is needed.
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 there is no parameter documentation burden. The description correctly focuses on output behavior instead, which is appropriate for a parameterless list tool.
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: it lists every published field note, with title, category, and date, newest first. It clearly distinguishes itself from get_field_note (read one note) and search_field_notes (search within notes) by framing the list as the full range before searching.
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 tells the agent to use this tool to see the full range of what has been written before searching within it, then use get_field_note to read a note in full. This gives a clear workflow and points to an alternative without needing to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The scheduled dates for the private six-person product roundtable in Yerevan, with how many guest seats remain on each. Use this to answer when the next table is or whether a given date still has room, and to get the exact startsAt value that request_table_seat needs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| tables | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare `readOnlyHint: true`, so the read-only nature is covered. The description adds useful behavioral context by explaining the data returned (dates and remaining seats) and that the output is suitable for answering specific questions. It does not contradict annotations and provides enough beyond the structured hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded: it states what the tool provides, then gives concrete use cases. Both sentences earn their place, and there is no redundant repetition of the title or 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?
For a zero-parameter read-only tool with an output schema, the description is complete. It explains the purpose, the kind of information returned, and how the output connects to a sibling tool. The existing annotations and output schema cover the remaining mechanical details, so nothing critical 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 has zero parameters, so there is nothing to document beyond what the input schema already implies. The description adds relevant context by naming the `startsAt` value and its relationship to `request_table_seat`, which helps an agent understand how to use the output even though no parameters exist.
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 resource (scheduled dates for the private six-person product roundtable in Yerevan) and what it provides (dates and remaining guest seats). It also differentiates itself through the mention of the exact `startsAt` value needed by `request_table_seat`, making its role distinct from sibling 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?
The description explicitly tells an agent when to use this tool: to answer when the next table is, whether a date has room, and to get the `startsAt` value for `request_table_seat`. This gives clear practical usage context and connects it to a sibling tool without ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Ask for one of the five guest seats at a Yerevan Product Coffee table. Call list_upcoming_tables first and pass one of its exact startsAt values. This sends a real request to a real person, so it takes two calls: call it once to see exactly what would be sent, show that to the person it is about, then call it again with the same values and confirm: true. A request is not a booking — Hovhannes reads each one himself and replies within 3–5 days, and no seat is held until he does.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Their email address. The reply and the confirmation both go here, so it has to be one they read | ||
| phone | Yes | Their phone number with its country code, like +374 11 22 33 44. Used only on the evening itself and deleted if the request is closed | |
| confirm | No | Leave unset or false to validate and preview without sending anything. Set to true only after the person has seen the preview and agreed to it | |
| building | No | What they are building, in their own words. Optional but read | |
| fullName | Yes | The applicant's full name, as they would write it | |
| eventStart | Yes | Which table. The exact `startsAt` from list_upcoming_tables is best, but the calendar day on its own ("2026-09-10") or the word "next" also resolve against the real schedule | |
| motivation | No | Why this table, now. Optional | |
| linkedinUrl | Yes | Their personal LinkedIn profile URL (linkedin.com/in/…). Required: seats are chosen on who sits together, which cannot be judged from a name. Company pages, posts and shortened links are refused | |
| perspective | Yes | The perspective they bring: founder (Building or validating a product of your own.); product (Deciding scope, priority, discovery, and delivery.); design-research (Bringing users, flows, and evidence into the room.); engineering (Turning product intent into something real.); growth (Positioning, demand, distribution, retention.); customer (Sales, support, and discovery signals.); hybrid-other (More than one lens, and that is fine.) | |
| contribution | No | What they can offer the other five people. Optional | |
| discussionQuestion | No | The one real decision or trade-off they are stuck on and want the table's help with. Optional, and the single most useful thing to include |
| Name | Required | Description |
|---|---|---|
| table | No | |
| status | No | |
| message | No | |
| duplicate | No | |
| submitted | Yes | |
| dailyLimit | No | |
| willSubmit | No | |
| instruction | No | |
| privacyNote | No | |
| alreadyRequested | No | |
| needsConfirmation | No | |
| whatHappensOnConfirm | No | |
| confirmationEmailedTo | No | |
| confirmationEmailStatus | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the call 'sends a real request to a real person,' which goes beyond the readOnlyHint=false annotation by explaining the human side effect. It also explains the dry-run vs confirmed behavior, manual review by Hovhannes, and the 3–5 day delay, none of which the annotations convey.
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?
Four sentences cover purpose, prerequisite, workflow, and expectations without repetition. The most actionable instructions ('Call list_upcoming_tables first') are front-loaded, and no sentence is 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 tool with 11 parameters, a two-call confirmation workflow, and human async review, the description covers the essential operational context: what to do first, what the first vs second call does, and what outcome to expect. An output schema exists, so return-value details are not required here; nothing an agent needs to invoke this correctly 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%, and the schema descriptions already provide detailed guidance for every parameter, including eventStart resolution and confirm semantics. The tool description reinforces 'pass one of its exact startsAt values' and 'confirm: true' but adds no new per-parameter meaning, so the 3 baseline for high schema coverage 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 opens with a specific verb and object: 'Ask for one of the five guest seats at a Yerevan Product Coffee table,' which names the exact resource and distinguishes it from listing or note tools. It further orients by referencing list_upcoming_tables, making clear this tool consumes that listing and is not itself a listing tool.
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 an explicit prerequisite: 'Call list_upcoming_tables first and pass one of its exact startsAt values,' and a mandatory two-call pattern with confirm:true. It also defines when the tool is not appropriate by stating 'A request is not a booking' and noting no seat is held for 3–5 days.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Hovhannes Hovhannisyan's written field notes on product planning, MVP scope, and building with AI agents. Returns the closest notes with a short excerpt and a link. Use this when asked what he has written or thinks about a product topic, then get_field_note to read one in full.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What to look for, in words |
| Name | Required | Description |
|---|---|---|
| notes | Yes | |
| query | Yes | |
| matchCount | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint, and the description adds helpful behavioral detail: it returns the closest notes with a short excerpt and link. This clarifies the output shape beyond the schema. The description does not contradict 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?
Three sentences cover purpose, return behavior, and usage guidance with no fluff. The core action is front-loaded, and every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter read-only search tool with an output schema, the description gives enough context: what to search, what to expect in results, and how to continue with get_field_note. Nothing critical 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, but the description adds meaning by scoping what the query should target: the author's product-planning, MVP-scope, and AI-agent notes. This helps an agent formulate better queries than the generic 'What to look for, in words' schema text alone.
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 verb and resource: searching Hovhannes Hovhannisyan's written field notes, with topic boundaries. It also distinguishes the tool by noting it returns the closest notes with an excerpt and link, setting it apart from get_field_note and list_field_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?
The description gives an explicit usage trigger: 'Use this when asked what he has written or thinks about a product topic.' It also names get_field_note as the follow-up for reading a note in full. It does not explicitly contrast with list_field_notes, but the guidance is still clear and actionable.
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_field_noteget_sprint_detailslist_field_noteslist_upcoming_tablesrequest_table_seatsearch_field_notesDiscover tech events, startup meetups, AI events across 8 cities — including hidden ones.
Open data: 1,590 JTBD hypotheses with cold-traffic test results and cost per lead. CC BY 4.0
Product context for AI agents: evidence, opportunities, initiatives, and decisions.
Pre-vetted senior LATAM engineers for US startups: hiring leads, open roles, applications.
Add one secure layer between your agents and this server.
