Error Database

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

No annotations are provided, so the description carries the full burden and leaves major traits undisclosed: 'clear' wipes all data but is not flagged as destructive or irreversible, there is no mention of persistence scope (session vs project vs global), no side effects noted for 'capture' (does it create or update patterns?), and no confirmation of what 'check' or 'search' actually do under the hood.

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 action-per-heading layout is front-loaded and scannable, with required markers inline. It is slightly padded by restating enum values already present in the schema (category, severity), but nothing is wasted at the sentence level.

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 21-parameter, eight-action tool with no annotations and no output schema, the description should cover per-action return shape, the destructive 'clear' semantics, and the format/agent_id parameters. It defines what each action does but leaves an agent unable to predict results or side effects of the riskiest operations.

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 only 48%, but the description compensates meaningfully by mapping parameters to the action that consumes them and marking required ones per action — information the flat schema does not convey. It still omits behavioral fields the schema leaves bare: format (json/text), agent_id, tags, limit semantics, and what file is used for in 'check'.

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 names a concrete resource (error pattern database for AI mistakes) and enumerates eight distinct actions (capture, check, search, stats, patterns, correct, report_fp, clear), so an agent can map intent to action. It does not, however, differentiate itself from strongly overlapping siblings such as mcp_m7_check_errors and mcp_m7_get_patterns, so the agent can't tell which tool to reach for without opening both.

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?

Each action gets a one-line gloss, which implies usage, but there is no explicit when-to-use/when-not guidance, no workflow sequencing (e.g., check before writing, capture after a correction), and no routing to mcp_m7_check_errors even though 'check' duplicates it in name. With 39 sibling tools the absence of any disambiguation is a real gap.

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