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

Annotations already establish readOnly/destructive/openWorld=false, so the bar is lower; the description still adds substantial behavior: the 3000-char cap and empty-string-when-unset for `custom_instructions`, and `null` when a model lacks a FINANCE.md, plus the presence of `validation_errors` and parsed `front_matter`. It does not cover auth/latency, but for a read tool this is 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.

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

Front-loaded with the core purpose, but the body is two very dense sentences packed with nested parentheticals and an eleven-item inline list, which reads closer to a data dump than a scannable spec. Every clause carries information, yet the structure makes it harder to parse than it needs to be.

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?

There is no output schema, so the description carries the return-shape burden entirely, and it does so thoroughly: field names, types, null/empty semantics, and the optional guide. Nothing an agent needs in order to call this correctly or interpret the result is 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 coverage is 100%, so baseline is 3, but the description adds real meaning: it clarifies that `model_id` scopes the `finance_md` portion and that `include_guide: true` injects the full `guide` with its section list. That goes beyond the schema's terse one-liners.

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+resource (returns the conventions values are expressed in) and immediately enumerates the two concrete payloads, `custom_instructions` and `finance_md`. The subject matter is unmistakably distinct from siblings like get_model or list_models, so an agent can route to it without inference.

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?

Explains the conditional trigger for `finance_md` ('when a model is targeted') and notes the alternatives for the same content ('also delivered in the handshake instructions', 'also the resource modeling-guide://reference'). It gives clear context and a redundancy pointer, though it never says explicitly when to prefer this tool over fetching the guide resource.

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