DreamAgent Cloud

dreamagent_chat

WRITE ACTION — builds, modifies, or fixes an EXISTING project with a natural-language instruction. Use ONLY when the user clearly asks for a change ("add X", "fix Y", "change the theme"). If the user is only asking for advice, analysis, review, or suggestions ("what could be improved?", "review my bot"), do NOT call this — answer from the project's info instead; a review request is not an edit.

Describe ONLY the desired change — DreamAgent's AI automatically handles code, tests, rebuild, and redeployment. Completed changes are saved and committed automatically.

ASYNCHRONOUS: returns immediately with the session_key; monitor with dreamagent_get_edit_progress (or dreamagent_get_chat_status with the returned session key) until a terminal state. Report success only after run_status reaches 'completed'. Edits consume the user's AI credits.

ERRORS (actual returns): failures come back as text starting with 'ERROR:'. If the edit was rejected before starting, the text says 'the edit was NOT started' plus the reason — HTTP 402 insufficient credits, 409 another edit already active, 423 session lock held by another session, 404 wrong project id, 401 no account connected. Treat the edit as failed/cancelled only when a status tool says so.

ONE EDIT AT A TIME: never start another modification on the same project while one is running — check progress first and wait.

Input Schema

TableJSON Schema

Name	Required	Description
`message`	Yes	the desired change (what + any behavioral constraints).
`project_id`	Yes	the project to modify.
`new_session`	No	optional — start a fresh session for a new topic.
`session_key`	No	optional — continue a specific development session.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses asynchronicity (returns immediately with session_key), the need to monitor to a terminal state, credit consumption, error formats with specific HTTP codes, and a one-edit-at-a-time concurrency constraint. This adds substantial behavioral context well beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with clear section headers (WRITE ACTION, ASYNCHRONOUS, ERRORS, ONE EDIT AT A TIME). Every paragraph carries essential information about invocation, monitoring, error handling, and concurrency, with no unnecessary filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (async, write action, error handling, concurrency), the description is complete. It covers what to do before calling, what happens on return, how to determine success, how to interpret errors, and what not to do. The existence of an output schema also reduces the need to explain return values in the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds guidance for the message parameter ('Describe ONLY the desired change') and mentions session_key in the async return context, but does not add new semantics for new_session or session_key beyond the schema's existing descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'WRITE ACTION — builds, modifies, or fixes an EXISTING project with a natural-language instruction,' using a specific verb and resource scope. It clearly distinguishes this tool from sibling tools by positioning it as the edit/change action, and explicitly excludes review/advice requests.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance ('Use ONLY when the user clearly asks for a change') and when-not-to-use guidance ('If the user is only asking for advice, analysis, review, or suggestions... do NOT call this'). It also names the monitoring sibling tools (dreamagent_get_edit_progress, dreamagent_get_chat_status) as alternatives to use after invocation.

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

All DreamAgent Cloud tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose: create vs. list vs. status, session vs. edit vs. project, and cancel vs. release lock. The three status tools are explicitly differentiated by what they monitor (session, latest edit, deployment).

Naming Consistency5/5

All tools follow the `dreamagent_verb_noun` pattern, with verbs like create, list, get, cancel, release. Retrieval is consistently split: `get_*` for single statuses and `list_*` for collections.

Tool Count5/5

12 tools is well-scoped for a cloud AI project management platform. Each tool addresses a distinct operation, covering creation, monitoring, editing, sessions, and integrations without unnecessary redundancy.

Completeness4/5

Core workflows are covered: create/list/status for projects, sessions management, edit/cancel/progress, and credential listing. Minor gaps exist—no project deletion, no env var updates—but these are not critical for the primary AI edit and deployment flow.

Resources

Need Help?