upgrade_project

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the mutation and safety profile is known. The description goes beyond that with genuinely additive behavior: the rewrite happens in one transaction (atomicity), it refuses any rewrite that changes an answer (a semantic-preservation invariant), and it details what dry_run previews. It omits failure/rollback specifics when dry_run=false, keeping it out of the top band.

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 front-loaded sentence that leads with the verb and resource, then appends the safety invariant and parameter notes. Dense but no filler; the semicolon-packed clause about dry_run and choices is slightly overloaded, which is the only thing keeping it from a 5.

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?

An output schema exists, so return values need not be described, and annotations cover the safety profile. Still, for a destructive, transactional mutation with 0% schema coverage, the two undocumented concurrency/safety parameters (idempotency_key, expected_revision) are a real gap an agent would need to call this correctly in repeated or concurrent use.

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 0% for 5 parameters, so the description must carry the load. It explains dry_run (the default, previews rules/proof/diff) and choices ({key: option} answers pending choices), two parameters well. It says nothing about idempotency_key or expected_revision, which matter a lot for a destructive mutation, leaving 3 of 5 parameters undocumented in both schema and description.

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: rewrite a package's legacy forms to the current ones, with the safety constraint that answer-changing rewrites are refused. This is clearly distinguishable from siblings like validate_project or diff_project. It stops short of naming those siblings explicitly, so it doesn't reach the top band.

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?

The description implies the intended workflow by noting that dry_run is the default and that it previews rules, proof and diff, which guides an agent toward preview-then-apply. However, it never says when to prefer upgrade_project over validate_project, diff_project or impact_project, nor when a caller should pass dry_run=false.

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