Write blog

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

Beyond annotations, it discloses that saving with body returns soft Voice DNA warnings, that direct generation sends context to Anthropic, and that fatal phrase violations are retried once before refusal to save. It also states that nothing is published to a website and that source credit must be retained. These are meaningful behavioral traits not captured by the readOnly/openWorld/idempotent/destructive hints.

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 dense but front-loaded, moving from the core purpose to sibling alternatives, then mode behavior and credit constraints. Every sentence carries operational information, including the return behavior and external-send caveat. There is no filler or repeated schema content.

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 16-parameter tool with no output schema, the description covers the essential operating modes, return behavior, warning behavior, credit requirement, and external Anthropic call. The schema handles the detailed parameter semantics at 100% coverage, so the description does not need to restate every optional field. Nothing critical for correct invocation appears missing.

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 all 16 parameters. The description adds useful mode-level semantics: body absence triggers grounding, body presence saves a draft, direct generation requires the saved Anthropic key, and source credit must not be suppressed. It does not explain every optional field, but it adds enough beyond the schema to merit a 4 rather than the baseline 3.

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 states a specific dual verb-and-resource purpose: prepare grounding for a blog article or save a credited Markdown draft in the local Writing Studio. It immediately distinguishes the tool from siblings by naming write_tweet and generate_script for other content types. An agent can identify the resource and scope without opening the 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?

It explicitly says to use this for long prose and routes tweets/threads to write_tweet and video scripts to generate_script. It also explains the key mode split: omit body for grounding, include body to save a draft, and use direct generation only when explicitly requested. This gives clear when-to-use and when-to-use-alternatives guidance.

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