Create a privacy session to scope in-memory token mappings for masking sensitive content and code identifiers before LLM prompts, then restore originals from responses.
Create a new session. Duplicate IDs are errors; TTL is 1..86400 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | content_words | |
| strategy | No | bracket | |
| session_id | No | ||
| ttl_seconds | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v2.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses that duplicate IDs are errors and that TTL is constrained to 1..86400 seconds, but it omits what a session enables, whether creation is idempotent, permissions or auth requirements, and what the caller should expect beyond the output schema.
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 short sentences with the core action front-loaded and no filler. Its brevity is efficient, though it leaves important semantics unexplained rather than being verbose.
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 four-parameter session-creation tool with no annotations and no parameter descriptions, the definition is materially incomplete. The output schema can cover return values, but the description still fails to explain what session creation does behaviorally and what mode and strategy control.
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 explain all four parameters. It adds useful meaning only for ttl_seconds (range 1..86400) and implicitly for session_id (duplicate IDs are errors), while mode, strategy, and their allowed values or effects are left entirely undocumented.
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 and resource: "Create a new session." This clearly distinguishes creation from sibling operations like clear_privacy_session and get_session_stats, though it never clarifies that the session is a privacy/masking session.
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 create a session versus using mask_text, mask_code, get_session_stats, or clear_privacy_session. The only usage-adjacent information is the duplicate-ID error condition and TTL bounds.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.