Prism MCP

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

With no annotations provided, the description carries full behavioral disclosure. It reveals critical runtime traits: synchronous execution ('runs synchronously so you will know when it is safe'), duration ('up to 60 seconds'), backend-specific behavior (local vs. Supabase), and mechanical details ('SQLite reclaims page allocations only when explicitly vacuumed').

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?

Four tightly focused paragraphs with zero filler: 1) Purpose, 2) Prerequisites/mechanics, 3) Backend exceptions, 4) Performance warning. Every sentence advances understanding; the synchronous warning is bolded for visibility. Excellent information density.

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 maintenance tool with no output schema, the description comprehensively covers prerequisites (deep_storage_purge), execution model (synchronous, 60s duration), environmental constraints (local SQLite vs remote Supabase), and safety implications. No gaps remain for correct invocation.

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 coverage is 100%, so the schema fully documents the `dry_run` parameter. The main description text does not mention the parameter or add usage examples beyond what the schema provides. Baseline 3 is appropriate when the schema carries the full semantic load.

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 ('Reclaim disk space') and resource ('SQLite database'), clearly stating the tool performs VACUUM operations. It distinguishes from siblings by explicitly referencing `deep_storage_purge` as the prerequisite operation, clarifying this is a compaction follow-up rather than a general maintenance tool.

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 when-to-use guidance ('Best called after `deep_storage_purge` removes many entries') and contextual prerequisites. Also clarifies backend limitations ('For remote (Supabase) backends, returns guidance...'), effectively stating when not to use the tool for actual vacuuming and what alternative path to take.

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