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

Annotations declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, but the description adds far more: merge semantics (matching code_id overwrites, new code_ids append, unspecified files are preserved), that quality evaluation/diagrams/version/status are generated server-side, that version increments per save, that login is required, and the 400 error when a code_id was not PUT. This is exactly the kind of context annotations cannot carry.

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?

Front-loads the purpose well and uses labeled sections (merge rules, input, output), but it is dense and long, with several facts (is_root max 1, workspace_id behavior) duplicated verbatim from the schema, which dilutes rather than concentrates the signal.

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?

With no output schema, the description still states the return shape (id plus diagram URL) and covers auth requirements, server-side side effects, merge/preserve rules, and error conditions. An agent has everything needed to invoke this mutation correctly, including the prerequisite confirmation of the target workspace.

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 100%, so the schema already documents every parameter including adl_root, overview, workspace_id and the is_root flag. The description restates the input list and the two ADL-root-passing modes, but adds little that the schema descriptions do not already contain, so the baseline of 3 is appropriate.

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?

States a specific verb and resource: it commits files previously PUT to the request_upload_url/batch_request_upload_url staging URLs into an IceShore project's codes, creating new projects or merging into existing ones. It explicitly names the sibling tools it is not (save_content's full replacement, delete_code for deletion), so an agent can distinguish it without opening any schema.

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 context (after a curl PUT to staging), when-not-to-use (file deletion is not handled — use delete_code or save_content), and the key alternative distinction (MERGE appends/updates vs save_content's full replacement). The workspace_id requirement even spells out that the agent must confirm the target workspace with the user before calling.

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