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

The description discloses the write-oriented behavior of record and update, including the special constraint that superseding requires supersededById. It adds meaningful context beyond annotations by explaining that ADRs survive reindexes and are anchored to symbols/files/projects. It does not describe return formats or complete side effects, but the annotations offer no contradictory signals and the description is honest about mutating operations.

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 compact, front-loaded with the core concept, and organized into clear operation bullets. Every sentence carries information: persistence behavior, anchoring, and per-op requirements. There is no filler or redundant repetition of the schema.

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 14 parameters, multiple operations, and no output schema, the description covers the essential patterns an agent needs to call the tool correctly. It defines anchors, required fields per operation, and filtering options. Minor gaps remain, such as not mentioning the feedback piggyback field or the projectId default, but the schema fully documents those and the description handles the highest-risk decisions.

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 baseline is 3. The description adds valuable op-conditional semantics, such as record needing title+decision, anchor alternatives (repository+symbolPath vs filePath vs project-wide), and update requiring id with specific status handling. This goes beyond the flat schema descriptions and clarifies parameter relationships.

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 identifies the tool as managing architecture decision records, explains the core concept (WHY behind code), and enumerates the three operations record/list/update. It also differentiates from the sibling find_node by noting that find_node attaches a node's decisions, so the agent knows which tool handles retrieval vs. management.

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 gives per-operation usage rules: record requires title+decision and anchor selection, list filters by specific fields, and update requires id plus status transitions. It also points to find_node as the place where a node's decisions are attached, implying when the agent should look elsewhere. It does not explicitly state when not to use adr, but the op-specific guidance is clear enough for correct selection.

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