export_claude_md

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

With no annotations, the description carries full burden. It discloses the content sources but does not clarify whether the operation is read-only (e.g., no side effects), the output format, or file overwriting behavior. Listing included content provides moderate transparency, but security/permissions and return specifics are missing.

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 a single, well-front-loaded sentence that immediately conveys purpose and content scope. Every part is essential and adds value without redundancy.

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 simple input schema (one undocumented optional parameter) and no output schema or annotations, the description should fully compensate by explaining parameter behavior and return format. It fails to do so, focusing only on content aggregation without covering usage details or output characteristics.

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 max_constraints (integer, optional) has 0% schema description coverage and is not explained in the description. The description provides no guidance on what this parameter controls or its default, leaving agents to guess.

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 generates a CLAUDE.md document from the knowledge graph, specifying included content categories (constraints, decisions, bugs, co-edit patterns). This distinguishes it from sibling tools like get_constraints or get_decision_log, which focus on individual aspects.

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 implies the tool is for generating a comprehensive document aggregating multiple knowledge graph elements, but does not explicitly state when to use it instead of more specific siblings (e.g., get_constraints). No exclusions or alternatives are mentioned.

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