jitprompt gives your agents just-in-time instructions. Upload your docs as they are, and your agent gets the right section over MCP at the moment it needs it, instead of 20k tokens of system prompt every turn.
Scored across 3 tools
get_toc (browse the map), search_instructions (find by query), and get_section (fetch full text by id) are largely distinct, and the descriptions explicitly explain when to use each over the others. There is mild overlap between get_toc-with-document_id and search_instructions since both surface sections, but the docs steer you correctly.
All names are snake_case and readable, but the verb conventions vary: two use get_ (get_section, get_toc) while one uses search_. get_toc is also slightly abbreviated relative to its siblings, though still predictable and clear.
Three tools is on the thinner edge of the ideal range, but for a focused instruction-retrieval server each tool (map, search, fetch) earns its place with a clear role. It is not padded or over-engineered.
The read-only retrieval lifecycle is well covered: discover documents (get_toc), find relevant sections (search_instructions), and read them fully (get_section). No write operations exist, but the domain is guidance lookup, so the surface is essentially complete with only negligible gaps.
Fetch the full text of one instruction section by its id (from get_toc or search_instructions), with the document it belongs to. Always read the whole section before acting on it — rules and their exceptions live together.
| Name | Required | Description | Default |
|---|---|---|---|
| section_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It usefully discloses that the response includes the parent document and warns that rules and exceptions live together (a real behavioral caution against acting on fragments), but says nothing about permissions, failures on invalid ids, size/pagination, or rate limits.
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, no padding: the first defines the operation and its input source, the second delivers the safety directive. Everything is front-loaded and each 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?
An output schema exists, so return values need not be explained, and the description still notes the document payload. For a one-parameter retrieval tier of a known workflow, the only mild gap is error behavior for bad ids, which is a minor omission.
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 single parameter is a bare string, so the description is the only source of meaning — and it supplies the crucial provenance ('its id, from get_toc or search_instructions'). Format specifics of the id itself remain unspecified.
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 ('Fetch the full text of one instruction section by its id') and goes further by naming where the id originates (get_toc or search_instructions), which distinguishes it from both siblings. An agent can tell this is the leaf/retrieval step rather than the listing or searching step.
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 clear context for use: the id must come from get_toc or search_instructions, implying this tool is used after one of those. It adds a usage directive ('Always read the whole section before acting on it'), but does not state any when-not condition or explicit alternative for the retrieval itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Map of the instruction documents available to you: one entry per document with a one-line summary of what it covers and how to use it. Small documents list their sections inline (id, title, summary); large ones show a section count and how to expand them. Call this at the start of a conversation and again whenever the conversation moves to a topic or system you haven't checked guidance for. Cheap; safe to call repeatedly.
In a large collection the map is condensed (document lines, titles, or just an overview) and says so; then pass query.
query: what you are about to do (e.g. "checking a product's eligibility rules before an application"). Lists only the documents relevant to it, best first — the map for the task at hand.
document_id: pass a document's id (as shown in the map) to list every section of that one document. Do this to browse a document you need to read through. To find a specific rule, identifier, error code or table, call search_instructions instead — it is cheaper than expanding a large document and reading its section list.
Ids in the output are short prefixes; pass them as-is to get_section or get_toc.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| document_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and mostly meets it: it discloses cost ('Cheap; safe to call repeatedly'), that output is condensed in large collections and self-announces this, and that ids are returned as short prefixes usable as-is elsewhere. It does not cover failure modes or error behavior, so it falls 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?
Front-loads the core definition and keeps each parameter block focused on a single use case. It is longer than most definitions but nearly every sentence adds routing or behavioral information; the final line about short prefixes is slightly redundant given the earlier mention of ids.
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?
An output schema exists, so return values need not be explained, yet the description still conveys the shape and variability of the map (inline sections vs. section counts vs. condensed overview). For a two-parameter, zero-required navigation tool, 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 0%, so the description must compensate, and it does: it explains what query should contain ('what you are about to do') with a concrete example, and that document_id takes an id shown in the map to list that document's sections. Both optional parameters' semantics and interaction with the map output are fully specified.
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?
Opens with a concrete metaphor-plus-definition of the resource ('Map of the instruction documents available to you') and specifies exactly what an entry contains. It is clearly distinguishable from get_section (section listing) and search_instructions (rule lookup) without opening either 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 ('Call this at the start of a conversation and again whenever the conversation moves to a topic or system you haven't checked guidance for') and names the alternative for the adjacent task ('To find a specific rule, identifier, error code or table, call search_instructions instead') with the reason it is preferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find instruction sections relevant to what you are ABOUT TO DO. Call this before EVERY new topic, system, or data source you engage with — not just once per conversation. If the user's question shifts to a different system, product or task than the one you last checked guidance for (e.g. from refunds to account closures, or from one product to another), call this again before acting, even if you already called it earlier in this conversation. Describe your plan and the guidance you need — e.g. 'writing a refund email to an enterprise customer' or 'checking the eligibility rules for a product application' — NOT the user's question verbatim. Name the product, system or identifier when you know it. Returns whole sections grouped by document, best document first; a small document comes back whole, so read it as one piece.
| Name | Required | Description | Default |
|---|---|---|---|
| plan | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden, and it does disclose return behavior beyond the schema: whole sections grouped by document, best document first, and small documents returned in one piece. It says nothing about authentication, rate limits, or failure modes, which keeps it short of a 5 for an unannotated 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?
Front-loaded with the core directive and generally well organized, but the 'call again when the topic shifts, even if you already called it earlier' point restates the opening sentence's 'not just once per conversation' emphasis, adding some redundancy to an otherwise tight block.
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 search tool with an output schema already covering the return shape, the description supplies everything an agent needs: the trigger conditions, the query-construction guidance, and the grouping/ordering of results. Nothing material 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 single 'plan' parameter has 0% schema description coverage, so the description must compensate — and it does thoroughly, specifying that the agent should describe its plan and the guidance needed, give examples, avoid pasting the user's question verbatim, and name the product/system/identifier when known.
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 opening sentence gives a specific verb and resource: 'Find instruction sections relevant to what you are ABOUT TO DO.' The relevance-based retrieval framing implicitly separates it from get_section (fetch by id) and get_toc (listing), but neither sibling is named, so the differentiation is left to inference.
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?
Explicit and unusually prescriptive: call before every new topic, system or data source, not just once per conversation; call again when the user's question shifts to a different system or product, even if already called earlier. It also states what NOT to pass (the user's question verbatim) and what to pass instead, with concrete examples.
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_sectionget_tocsearch_instructions
Add one secure layer between your agents and this server.