mdshare

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

The description adds valuable behavioral context beyond annotations: it explains the performance implications of using output_path vs inline reading, specifies the approximate size threshold (~10KB) for optimization, and describes how response format changes when output_path is provided. While annotations cover safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true), the description provides practical implementation details that help the agent make better decisions.

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 efficiently structured with three focused sentences: the core purpose, conditional parameter behavior, and performance optimization guidance. Every sentence adds value without redundancy, and critical information (like the performance recommendation) is appropriately front-loaded.

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 the tool's moderate complexity, comprehensive annotations (readOnlyHint, destructiveHint, idempotentHint), and 100% schema coverage, the description provides excellent contextual completeness. It covers purpose, usage guidance, performance considerations, and parameter semantics without needing to explain return values (which are adequately described in the text).

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?

With 100% schema description coverage, the baseline is 3. The description adds meaningful context: it explains when 'key' is optional (for locally stored documents), clarifies that different key types are accepted (admin, edit, comment, or view), and provides the performance rationale for using 'output_path' with the ~10KB threshold. This goes beyond the schema's parameter descriptions.

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 specific action ('Read a markdown document from mdshare') and resource ('document'), distinguishing it from siblings like 'upload_markdown' or 'patch_document'. It explicitly mentions the return value ('Returns the content') and context-specific behavior for locally stored documents.

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 description provides explicit guidance on when to use alternatives: it states 'PREFER output_path over inline reading for large documents' and explains the performance trade-off. It also clarifies when the 'key' parameter is optional based on document storage location, offering clear context for parameter usage.

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