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

Annotations only cover the safety profile (not read-only, non-destructive, open-world); the description adds substantial context beyond that: asynchronous return with session_key, automatic code/test/rebuild/commit behavior, AI-credit consumption, a one-edit-at-a-time concurrency rule, and concrete error semantics (HTTP 402/409/423/404/401 and 'ERROR:' prefixes).

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?

Lengthy, but every block is labeled and front-loaded (WRITE ACTION, ASYNCHRONOUS, ERRORS, ONE EDIT AT A TIME, SUPERPOWERS), so an agent can scan for the relevant rule. Slightly verbose, with a few restatements (e.g., the failure/terminal-state caveat appears twice), keeping it short of a 5.

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 an async mutation tool with an output schema, the description covers everything an agent needs before and after calling: how to invoke, that it returns immediately, which tools to poll, when success can be reported, credit impact, and the concurrency and error envelope. No material gap remains.

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, but the description adds real meaning on top: it instructs that the message should describe ONLY the desired change and that the agent handles the rest, and it ties session_key/new_session to session continuation vs. fresh topics. It does not add format constraints beyond that.

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?

Opens with 'WRITE ACTION — builds, modifies, or fixes an EXISTING project with a natural-language instruction', giving a specific verb class, resource, and scope. It explicitly separates itself from read/advice tools, so an agent can distinguish it from siblings like dreamagent_get_project_status or dreamagent_edit_file.

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?

Gives explicit when-to-use ('add X', 'fix Y') and when-not ('advice, analysis, review, or suggestions' → do NOT call). Also routes to siblings by name for monitoring (dreamagent_get_edit_progress, dreamagent_get_chat_status) and catalog lookup (dreamagent_list_superpowers).

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