record_decision

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

With no annotations provided, the description fully carries the behavioral burden. It discloses important side effects and behaviors: same-title inputs update the existing record, project names are auto-corrected or discarded, unregistered projects become team-common, code_refs trigger later revalidation, and the response contains project/project_hint and similar_existing signals. This is strong, useful transparency for a mutation-style tool.

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 front-loaded with the purpose, then organized by usage guidance and parameter semantics. It is longer than average, but every sentence adds useful information, and the length is justified by 9 parameters and complex side effects.

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?

The description is largely complete for a knowledge-base recording tool with no annotations: it covers when to use it, what each key parameter means, update/upsert behavior, project scoping, and deduplication guidance. The output schema reduces the need to describe return values. The main gap is not explicitly guiding an agent away from sibling tools such as record_note or record_learning.

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 description coverage is 0%, and the description compensates well for several parameters: title, author, code_refs, supersedes, and especially project. It explains nuanced behavior like project normalization and monorepo auto-correction. However, tags, context, and alternatives are not explained beyond what their names imply.

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 action: recording development decisions into a knowledge base, immediately searchable team-wide. It also gives concrete examples such as architecture/library/schema choices and tradeoff judgments. However, it does not explicitly distinguish itself from sibling tools like record_learning or record_note.

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?

It provides an explicit '언제 쓰나' section that lists clear use cases and advises updating an existing decision when similar_existing appears. It also warns against overwriting when the existing candidate belongs to a different project. It does not explicitly state when to prefer alternative sibling tools.

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