Ingest Spec

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

Annotations already indicate readOnlyHint=false (a write operation) and destructiveHint=false, so the agent knows it mutates data without destroying. The description adds that it parses specific formats and ingests into graph nodes, but does not disclose behavior such as whether it overwrites existing nodes, merges, or handles duplicate or invalid files. Some behavioral context is added beyond annotations, but not rich detail.

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-structured sentence that front-loads the action and resource. Every phrase earns its place: the supported formats are enumerated, and the destination ('graph nodes') is specified. No redundant or filler content.

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 tool with 3 parameters and no output schema, the description is fairly complete: it states the purpose, input types, and output destination. However, it lacks details on what the tool returns or what happens on success/failure (e.g., whether ingestion is idempotent or how it interacts with existing graph nodes). Since no output schema exists, such information would improve completeness, but the description covers the core use case.

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 documentation covers 100% of parameters, so the baseline is 3. The description mentions supported formats (markdown, gherkin) which maps to the 'format' parameter, but does not add any semantic details beyond the schema. It adds minimal value beyond what the schema already provides.

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 primary action ('Parse and ingest'), the resource ('a Markdown PRD, OpenSpec, or Gherkin BDD specification file'), and the outcome ('into graph nodes'). It is specific enough to distinguish from sibling tools like scaffold_spec or export_spec, which deal with creating or exporting specs rather than ingesting them.

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?

No explicit guidance is given about when to use this tool versus alternatives. The description does not mention prerequisites, when to choose this over import_graph or scaffold_spec, or any exclusions. The usage context is only implied by the action description, which is insufficient for selecting among many graph-related tools.

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