Strip PII (emails, SSNs, credit cards, IPs, URLs) from text to stable placeholders before you pass it onward; the mapping is returned so YOU reveal replies locally. For true privacy run this on a LOCAL/sovereign engine (the text never leaves your machine) or use the client libraries — the strip belongs at your edge. Deterministic; pair with verify for a receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the mapping is returned for local reveal, that redaction is deterministic, that true privacy requires a local engine (implying this endpoint may not be fully private), and mentions pairing with verify.
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 three sentences, with the core function in the first sentence, privacy guidance in the second, and determinism/pairing in the third. Each sentence adds substantive info; no 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?
Given the tool's simplicity (one parameter) and no output schema, the description provides a good but not exhaustive account. It explains the return mapping conceptually but not its exact structure, and mentions determinism and verify pairing. This is sufficient but leaves a small gap regarding the format of placeholders/mapping.
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 a single 'text' string parameter with no schema-level description (0% coverage). The description compensates by clearly indicating that 'text' is the content to be stripped of PII and that it is passed onward. It adds the behavioral context of the input without repeating schema constraints.
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 'Strip' and identifies the resource (PII from text), explains the output (stable placeholders) and the context (before passing onward). It clearly distinguishes the tool's function from the listed siblings, none of which perform redaction.
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 provides clear usage context: use before passing text onward, and pairs with verify for receipt. It also advises running on a local/sovereign engine or client libraries for true privacy, which is an explicit alternative (though not a different tool). It lacks an explicit 'when not to use' but gives sufficient guidance.
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.