veto_session_save

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false but the description carries the real burden by disclosing this is a persistent write that bypassing via direct DB mutation 'corrupts state.' It also surfaces the MCP Sampling behavior for auto_summarize and the session_id update-in-place semantics. This adds substantive behavioral context beyond 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?

The description is longer than average (four sentences) but every clause earns its place: core purpose, trigger registration, a corrective warning, and two usage tips. The core purpose is front-loaded; the warning about bypassing the tool is well-placed near the top since it prevents a costly mistake.

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 11 parameters, zero required fields, and no output schema, the description is appropriately thorough. It covers the write semantics, project scoping, auto_summarize, and in-place updates. It could mention the absence of a documented return value, but with 100% schema coverage and rich param docs, agents have what they need to call it 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 description coverage is 100%, so the schema fully documents all 11 parameters. The description adds value on top by explaining key behaviors: auto_summarize's fallback behavior, session_id preventing 'session inflation when refreshing mid-conversation,' and the recommendation to omit summary/context/task_state when auto_summarize is true. This exceeds the baseline-3 expectation for full schema coverage.

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 opens with a specific verb+resource+destination: 'Saves the current session context to SQLite.' It clearly distinguishes itself from siblings like veto_session_restore (restoring) and veto_sessions_list (listing) by stating exactly what state-changing action it performs.

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?

Provides explicit trigger conditions ('when the user types veto_session_save / veto_save_session / save session') and a strong when-not-to ('never write a node script or INSERT into ~/.veto/veto.db by hand'). It also gives usage guidance for auto_summarize. It does not explicitly route to sibling save-vs-restore alternatives, which keeps it from a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.