anchor_context_traceCreate or inspect an immutable provenance anchor from a context digest, parent digests, and processing stage. No context content is stored. Production; subscription API key required.
| Name | Required | Description | Default |
|---|---|---|---|
| stage | No | ||
| operation | Yes | ||
| control_id | No | ||
| context_digest | No | ||
| parent_digests | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral traits beyond annotations: it explicitly states 'No context content is stored' (privacy guarantee) and 'immutable' (data integrity). Annotations already indicate idempotentHint=true and destructiveHint=false, which are consistent. The description does not contradict annotations and adds meaningful context about side effects and data retention policies.
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 two sentences totaling 20 words, front-loading the main purpose and then adding critical context. Every sentence earns its place: the first sentence defines the operation and inputs, the second clarifies data handling and production constraints. There is no extra fluff or repetition of what the schema already shows.
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 tool has 5 parameters, no output schema, and no parameter descriptions. The description explains the high-level purpose and a few parameters, but it omits what the tool returns (e.g., for 'check' operation) and the role of control_id. For a provenance tool with only two sentences of documentation, an agent lacks sufficient information to invoke it correctly without external knowledge. More behavioral details (e.g., response format, error states) are 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?
With 0% schema description coverage, the description carries the burden of parameter explanation. It covers three of five parameters: context_digest, parent_digests, and stage by naming them in the use case. The operation parameter is implied by 'Create or inspect' (anchor vs check). However, control_id is not explained at all, leaving its purpose ambiguous. The description adds moderate value but is incomplete for a schema with no descriptions.
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 creates or inspects an immutable provenance anchor using specific inputs: context digest, parent digests, and processing stage. This action is distinct from all sibling tools, which cover approvals, actions, quality, etc. The verb-resource pair is precise and leaves no ambiguity about the tool's core function.
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 no guidance on when to use this tool versus alternatives like record_action_receipt or other provenance-related siblings. It mentions 'Production' and a subscription API key as prerequisites, but does not explain scenarios for choosing 'anchor' vs 'check' operations. The lack of when-to-use or when-not-to-use instructions makes it hard for an agent to select the correct tool among 47 siblings.
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.
The tool set covers two domains (text processing and agent infrastructure) with many specialized tools. Text tools like inspect_text, scan_untrusted_text, sanitize_agent_context, and prepare_for_agent have overlapping risk signals but descriptions clarify distinct purposes. Action infrastructure tools like manage_action_challenge, manage_action_quorum, manage_action_reconciliation are well-differentiated but numerous, leading to potential confusion for an agent selecting among them.
All tools use snake_case with a verb_noun pattern (e.g., check_action, manage_task_contract, scrub_text). The verbs are diverse (check, manage, create, delete, record, inspect, etc.) but consistently applied. A few deviations like fingerprint_action and lock_action_intent still follow the style. Overall, the naming is predictable and homogeneous.
49 tools is excessive for a typical MCP server. The server tries to combine text preprocessing (10-12 tools) with a comprehensive agent infrastructure (30+ tools) into one surface. While each tool may serve a purpose, the count overwhelms the typical scope, making it hard for an agent to navigate efficiently.
The text processing suite covers scrubbing, inspection, redaction, validation, and detection thoroughly. The agent infrastructure covers idempotency, approval, signals, leases, budgets, deadlines, handoffs, and reconciliation. There are no obvious missing lifecycle states for the intended advanced agent framework. Minor gaps exist, such as no tool to list all active locks or signals, but these are likely out of scope.