cpu_set_syndicate_params

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

With zero annotations, the description carries the full burden and delivers: full-card replacement with silent default-revert data loss, on-chain wallet write, untouched manager/creation fields, and a prompt-injection warning to treat returned name/link as untrusted data. It even enumerates the exact failure conditions (not manager, over-long name/link, rate above 100%, undeployed registry).

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?

Long, but every sentence adds a distinct operational fact and the most critical warning ('REPLACES the entire card... NOT a partial patch') is front-loaded in sentence two. The mild redundancy ('Otherwise you will silently wipe fields you omit') deliberately reinforces the highest-risk failure mode and is earned.

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 a high-complexity, destructive, on-chain mutation with no annotations and no output schema, the description covers prerequisites, security, constraints, and failure modes exhaustively. The only notable gap is the success response — the description never states what the agent should expect back (confirmation, transaction hash, updated card) — which is a meaningful omission when no output schema exists.

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's main net-new contribution is the replace-not-patch interpretation — any omitted field reverts to its default — which materially changes how the agent must construct the rates object and link. The remaining parameter constraints (byte limits, 0–100 basis-point steps, empty string clears link) already live in the schema, so the added value is real but bounded.

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 a specific verb-resource-scope statement — 'Update a syndicate you manage' — and immediately disambiguates the tool's destructive semantics from a partial patch. By naming the read-only siblings (cpu_get_syndicate, cpu_get_syndicate_player_content), it is clearly distinguishable from the other syndicate tools in the sibling list (create, transfer, join, leave).

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?

Explicitly prescribes a read-before-write workflow: 'Read trusted fields with cpu_get_syndicate and read name/link separately with cpu_get_syndicate_player_content FIRST, then resubmit the full state with your edits applied.' It also states preconditions via failure conditions (must be manager, registry must be deployed), giving the agent clear criteria for when calling will fail.

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