Coach — adaptive 'what's next' in a subject: given completed unit ids, the next lesson whose prerequisites are met (grows with the student). Found, never generated.
| Name | Required | Description | Default |
|---|---|---|---|
| subject | No | ||
| completed | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It discloses a key trait: the tool 'finds' rather than 'generates' content, and it 'grows with the student' by respecting prerequisites. This is valuable transparency, though it doesn't mention side effects or error behavior; the 'found' wording implicitly suggests a non-mutating read operation.
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, well-structured sentence that front-loads the core purpose and then adds the key behavioral detail. Every phrase is informative, and it is concise without being vague.
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 the tool's simplicity (2 params, no output schema), the description covers purpose, inputs, and the adaptive behavior. However, it doesn't indicate the return format of the 'next lesson' or behavior when no lesson meets prerequisites. These omissions are notable but not fatal for this tool's complexity.
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. It explains that 'completed' is a list of unit IDs and 'subject' indicates the subject area, and it reveals the logic (prerequisites are met). This adds meaning beyond the bare schema, though it doesn't specify formats or how to identify the subject uniquely.
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 states the tool's function: recommending the next lesson for a subject based on completed unit IDs and prerequisite satisfaction. It uses specific language ('adaptive what's next', 'found, never generated') and distinguishes itself from sibling tools like coach_next by emphasizing the prerequisite-based, found-not-generated behavior.
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 clear usage context: call this tool when you have completed unit IDs for a subject and want the next lesson. It does not explicitly name alternatives or exclusions, but the input description implies when it is appropriate, which is sufficient for most cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools are near-duplicates: read_passage and resolve both fetch WEB text for a reference; word_study already includes every occurrence that word_occurrences returns; coach_next and coach_recommend both answer 'what's next.' Search/locate/cards_browse also overlap as discovery entry points, making tool selection ambiguous despite detailed descriptions.
Most names follow an object_verb snake_case pattern (cards_browse, study_create, seal_fetch), but there are many bare verbs/nouns (ask, audit, resolve, verify, canon, harmony) and inconsistent singular/plural pairs (card_get vs cards_browse, group_create vs groups_list, want_open vs wants_list). No camelCase, but the convention is not uniform.
86 tools is an extreme count for any single MCP server, far beyond the 3-15 well-scoped range; even a broad platform would be hard for an agent to navigate. Many tools belong to unrelated subdomains (coach, steward, mesh, calendar), making the surface unwieldy.
The want/offer flow has no accept/close tool, so an agent can open a want and offer a source but never see it resolved. Group and calendar coverage are one-directional (create/join only; no leave/delete/list/update), and there is no badge listing or way to update a study group. Core reading/verification/shelf flows are solid, but lifecycle gaps remain.