Read-only EngineerPro engineering library (118 book profiles) and software-engineering tools.
Scored across 7 tools
Most tools target clearly distinct resources: list_tools/find_tool deal with the tool catalog, list_library_books/search_library/get_library_book with books, and get_concept/compare_tradeoff with knowledge units. The main overlap is find_tool (search across catalog + guide bindings) versus list_tools (catalog listing), which an agent could slightly confuse, but the list-vs-search distinction is conventional and clear.
All seven tools use a consistent snake_case verb_noun or verb_object pattern (compare_tradeoff, find_tool, get_concept, get_library_book, list_library_books, list_tools, search_library). Verbs (get/list/search/find/compare) map predictably to their operations with no mixed conventions.
Seven tools is well within the ideal 3-15 range and each maps to a distinct operation (list, get, search across books/concepts/tools plus a tradeoff comparator). No redundant or filler tools are apparent.
The read-only library surface covers listing, getting, and searching books, concepts, tools, and tradeoffs, which is solid for a reference server. Minor gaps exist (no search/list for concepts or tradeoffs themselves—you must know the concept or tension name to fetch it), but agents can work around this via the book search.
Return one named engineering tension's opposing camps, a cited answer, and the books it's grounded in (EP-217).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Trade-off slug, e.g. microservices-vs-monolith. |
| Name | Required | Description |
|---|---|---|
| lane | Yes | |
| slug | Yes | |
| camps | Yes | |
| answer | Yes | |
| tension | Yes | |
| apex_url | Yes | |
| api_version | Yes | |
| grounded_in | Yes | |
| source_guide | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds that the result contains opposing camps, a cited answer, and grounding books, which is genuine return-content context. It stops short of noting that an unknown slug may fail or how large the payload is.
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 tightly packed sentence that front-loads the verb and resource. The only wasted token is the parenthetical '(EP-217)', which is opaque to an agent.
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 an output schema present, the description need not explain return structure, and it correctly focuses on purpose and payload character. The remaining gap is discoverability of valid slugs and when to prefer this over sibling lookup tools.
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 slug parameter already carries an example (microservices-vs-monolith), so the schema does the heavy lifting. The phrase 'one named engineering tension' reinforces that the slug must map to a known named tension, but adds no format or validity 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 verb ('Return') and a specific resource ('one named engineering tension') plus the payload composition (opposing camps, cited answer, grounding books). This clearly distinguishes it from siblings like get_concept or search_library, though the cryptic internal reference '(EP-217)' adds noise rather than clarity.
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?
No when-to-use guidance and no routing versus alternatives such as get_concept or search_library. The agent must infer from the name alone that this is the tool for a single named trade-off, and nothing explains how to obtain a valid slug.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Substring search across the SE tools catalog and its guide bindings (EP-219: bound step, construct, tension).
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query. | |
| limit | No | Max rows (default 20, max 50). |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| limit | Yes | |
| query | Yes | |
| tools | Yes | |
| api_version | Yes | |
| total_matching | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, closed-world behavior, so safety is covered. The description adds genuinely useful context beyond that: matching is substring (not fuzzy or semantic), and the searched corpus includes guide bindings, not just tool records. It does not cover pagination or result ordering, but it clears the lower bar set by 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 with no padding, and the search scope comes first. The parenthetical 'EP-219: bound step, construct, tension' is somewhat opaque internal jargon that may not help an agent, keeping it from a 5.
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 described, and the parameters are fully covered by the schema. The missing piece is routing guidance among the six siblings, which matters for a search tool competing with list_tools and get_concept.
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 both parameters are documented in the schema (including limit default and max). The description adds no syntax or format detail about 'q' or 'limit', which is acceptable given the schema does the work; baseline 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?
States a specific verb+resource: substring search over the SE tools catalog and its guide bindings. The scope ('across the catalog and its guide bindings') is concrete and distinct from a plain listing. It does not explicitly contrast itself with the closest sibling, list_tools, so it stops short of a 5.
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 says what is searched but never states when to use this instead of list_tools or get_concept, nor any prerequisites or exclusions. The reader must infer that a substring query implies this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return one engineering concept's definition, a cited ≤60-word answer, and the books it's grounded in (EP-217, derived from bicycle-guide's canonical guide bodies).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Concept slug, e.g. prompt-engineering-quality. |
| Name | Required | Description |
|---|---|---|
| lane | Yes | |
| name | Yes | |
| slug | Yes | |
| answer | Yes | |
| apex_url | Yes | |
| definition | Yes | |
| api_version | Yes | |
| grounded_in | Yes | |
| source_guides | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the safe read-only, closed-world profile, and the description adds genuinely new context: the answer is cited and capped at 60 words, and results carry the grounding books and a source lineage (bicycle-guide canonical guide bodies, EP-217). It does not say what happens for an unknown slug, which keeps it out of 5 territory.
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 wastes nothing and puts the payload shape before the provenance aside. The trailing "EP-217" internal code is opaque to an outside agent, but it is contained in a parenthetical and does not obscure the main claim.
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 tool with an output schema, the description covers purpose, return contents, and data provenance, so an agent has enough to call it correctly. Only the failure behavior for an invalid slug is left unstated, a minor gap given the output schema exists.
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 lone slug parameter is documented with a concrete example, so the schema does the heavy lifting. The description adds no further format or naming guidance beyond what the schema already provides, making 3 the correct 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 ("Return") and a specific resource ("one engineering concept's definition") plus the exact shape of what comes back. It implicitly separates itself from get_library_book, but it never names a sibling or states the distinction explicitly, so it stops short of a 5.
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?
There is no when-to-use or when-not-to-use guidance and no named alternative among the six siblings. The slug-based lookup model is only inferable from the parameter, leaving the agent to guess whether this or search_library is the right entry point.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return one library row plus its structured profile (thesis, model, instrument summary) when a sidecar exists.
| Name | Required | Description | Default |
|---|---|---|---|
| libraryId | Yes | Stable library id from list_library_books or search_library. |
| Name | Required | Description |
|---|---|---|
| year | Yes | |
| title | Yes | |
| author | Yes | |
| profile | Yes | |
| engGuides | Yes | |
| libraryId | Yes | |
| hasProfile | Yes | |
| api_version | Yes | |
| canonicalUrl | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the read-only, non-destructive nature. The description adds the key behavioral nuance that the structured profile is included conditionally, only 'when a sidecar exists,' which is useful beyond what annotations provide.
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 conveys the action, the target, and the conditional behavior without waste. 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 simple get-by-id tool with a rich output schema, annotations, and a well-described parameter, the description is nearly complete. The only minor gap is not stating what happens when no sidecar exists, though the conditional phrasing and output schema likely cover 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?
Schema coverage is 100% and the libraryId parameter already has a clear description. The tool description does not add additional parameter-level meaning, so a 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 states a specific verb ('Return') and resource ('one library row plus its structured profile'), and names the profile components. The 'one' qualifier clearly distinguishes this get-by-id tool from the list and search siblings.
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?
Usage is implied rather than explicit: the description implies this is for retrieving a single known book's profile, and the parameter schema mentions ids come from list_library_books or search_library. However, it does not explicitly state when to prefer this over search_library or list_library_books.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List books from the EngineerPro 118-book engineering library slice with lane tags and profile availability.
| Name | Required | Description | Default |
|---|---|---|---|
| lane | No | Filter by eng_guides lane, e.g. software-engineering. | |
| limit | No | Max rows (default 100, max 500). |
| Name | Required | Description |
|---|---|---|
| lane | No | |
| books | Yes | |
| count | Yes | |
| limit | Yes | |
| api_version | Yes | |
| total_matching | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description agrees by describing a read-only listing operation. The description adds modest context by specifying the 118-book slice and mentioning lane tags and profile availability, but it does not disclose other behavior such as ordering or pagination. Given the annotations and simple nature of the tool, this is adequate but not rich.
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 front-loaded sentence that states the action, resource, and output features with no filler. It is concise while still providing the essential scope information an agent needs.
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 list tool with two optional parameters, 100% schema coverage, and an output schema, the description plus annotations are nearly sufficient. The only minor gap is that 'profile availability' is not expanded, but this is likely clarified by the output schema, so nothing essential to invoking the tool 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?
Input schema coverage is 100%, describing both the lane and limit parameters fully. The description adds no meaningful parameter-level detail beyond hinting at lane tags, but with complete schema coverage the baseline 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 the specific verb 'List' with a clearly defined resource, the 'EngineerPro 118-book engineering library slice', and names the included fields (lane tags, profile availability). This distinguishes it from get_library_book, which fetches a single book, and search_library, which searches, so an agent can identify the intended operation.
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 does not say when to use this tool versus search_library or get_library_book. There are no explicit conditions, exclusions, or alternative tool mentions. The intended usage is only implied by the verb 'List' and the slice name, leaving the agent to infer tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Catalog of interactive SE tools with REST path hints.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| tools | Yes | |
| api_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the 'REST path hints' detail, which hints at return content, but does not disclose pagination, formatting, or scope limitations. With annotations present, this is adequate but not rich; the description adds modest contextual value.
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, short sentence that is immediately readable and front-loaded with the core purpose. Every word matters: 'Catalog', 'interactive SE tools', and 'REST path hints'. There is no unnecessary elaboration or redundancy.
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 that the tool has no parameters, is read-only (per annotations), and has an output schema (which presumably describes the returned catalog), the description is sufficient for an agent to understand the general purpose. However, the phrase 'REST path hints' is ambiguous without further explanation, and the relationship to the sibling tools is not clarified. Still, the output schema likely covers return details.
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 the input schema (100% coverage) leaves nothing undocumented. The description correctly avoids any parameter discussion, and the baseline of 4 applies because no parameter information is expected from the 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?
The description clearly identifies the resource as 'interactive SE tools' and indicates the action is listing/cataloging. It adds a distinctive detail ('REST path hints') that helps distinguish it from the library-related siblings. However, it doesn't explicitly use the word 'list' and the meaning of 'interactive SE tools' and 'REST path hints' could be more precise.
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?
There is no guidance on when to use this tool versus alternatives. The sibling names imply a different domain (library books), but no explicit comparison, prerequisites, or exclusion criteria are provided. The description alone does not help an agent decide between this and similar listing tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Substring search across title, author, lane tags, and classifier tags.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Search query. | |
| limit | No | Max rows (default 50, max 200). |
| Name | Required | Description |
|---|---|---|
| books | Yes | |
| count | Yes | |
| limit | Yes | |
| query | Yes | |
| api_version | Yes | |
| total_matching | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint, so the safety profile is covered. The description adds substring semantics, which is useful, but it does not disclose behavior like case sensitivity, ordering, or how matches are ranked.
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 sentence immediately conveys the operation and scope with no unnecessary detail. It is efficient and 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?
For a simple, read-only, two-parameter search tool with a full input schema and output schema, the description is sufficient. An agent has enough information to select and invoke the 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 coverage is 100%, so the schema documents both parameters. The description adds meaningful context by specifying that q searches across title, author, lane tags, and classifier tags, which goes beyond the generic 'Search query' schema 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?
The description states a specific verb ('search'), resource ('the engineering library'), and the exact fields being searched. This clearly distinguishes it from the sibling tools like get_library_book or list_library_books.
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 this tool is for substring-based lookup, but it does not explicitly explain when to use it versus list_library_books or get_library_book. No alternatives or exclusion criteria are mentioned.
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.
compare_tradeofffind_toolget_conceptlist_tools2 fields changedOutput schema / properties / tools / items / properties / binds_toAdded value: +{
+ "anyOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "construct": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "state": {
+ "enum": [
+ "bound",
+ "no-runnable-tools",
+ "no-funnel-row"
+ ],
+ "type": "string"
+ },
+ "step": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "step_name": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "tension": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "tool": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "tool",
+ "state",
+ "step",
+ "step_name",
+ "construct",
+ "tension"
+ ],
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+ ]
+}Output schema / properties / tools / items / requiredPrevious value: -[
- "slug",
- "name",
- "pill",
- "description",
- "restPath",
- "productHome"
-]New value: +[
+ "slug",
+ "name",
+ "pill",
+ "description",
+ "restPath",
+ "productHome",
+ "binds_to"
+]get_membership_offerget_membership_offerget_library_booklist_library_bookslist_toolssearch_libraryRead-only access to Compensation Professional's compensation-focused book library, query-shaped...
Read-only Pattern-Assist corpus for aspiring software engineers: grounded dev patterns with sources.
Industrial glossary, protocol reference, technical search and OEE calculation. Read-only.
Read-only access to Penwright's writing-craft book library, grounded guide metadata (card-level...
Add one secure layer between your agents and this server.