snapshot

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

Annotations indicate readOnlyHint=false (creating), destructiveHint=false (non-destructive draft), idempotentHint=false (each call creates new draft), and openWorldHint=true. The description adds detailed behavioral context: it is INSERT-only, creates a draft, explains the process (fuzzy match, recency-weighting, evidence tier), and mentions future integration ('Gemini integration ships later').

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 well-structured with sections (WHEN TO USE, HOW IT WORKS, EXAMPLES) and bullet points. Every sentence adds value without unnecessary verbosity.

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?

Despite no output schema, the description explains the output: a draft snapshot with evidence_tier and grounded_ratio, status='draft', and the required subsequent action (accept_snapshot). It covers the tool's behavior comprehensively.

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 single parameter 'topic' has full schema coverage (100%) with description, min/max length, and examples. The description adds meaning beyond schema: it explains the parameter is used for fuzzy matching against tags and titles, and that matching is recency-weighted.

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 purpose: 'Generate a state-shaped artifact for a topic from your saved memories.' It uses a specific verb ('Generate') and resource ('artifact'), and the description differentiates it from siblings like 'get_snapshot' and 'accept_snapshot' by detailing that it creates a new draft.

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 'WHEN TO USE' section explicitly lists use cases (architecture map, glossary, runbook, etc.) and mentions the slash command. While it doesn't explicitly say when not to use alternatives, the context is clear and differentiates from other snapshot-related tools.

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