register_model

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds genuinely useful scope: 'replace' signals overwrite semantics, while 'without moving its artifacts or refreshing upstream' bounds the blast radius the destructive hint leaves ambiguous. It does not mention the confirm/plan preview behavior, which would be the final piece.

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?

A single tightly-written sentence with the action and its two key exclusions front-loaded; every clause earns its place.

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 a full output schema and rich annotations, the description covers the essential action and its non-effects. The only gap is not mentioning the dry-run/confirm path, which schema carries but a caller scanning descriptions might miss for a destructive operation.

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% and both parameters are documented in-schema, including the important 'confirm=false returns its plan' semantics. The description adds no parameter-level meaning beyond the schema, so baseline 3 applies.

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 pair (register/replace) and resource (a local model), and carves out scope with 'without moving its artifacts or refreshing upstream', which distinguishes it from download_model and refresh_catalog. No sibling is named explicitly, so it falls short of a 5.

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?

'Register or replace a local model' implies the precondition that the weights already exist locally, and the negations hint at what this tool deliberately does not do. However, no alternative tool is named and there is no explicit when-not guidance (e.g. 'use download_model if the weights are not on disk').

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