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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, yet the description still adds substance: the explicit 'never accepts a version or changes infrastructure' guarantee, the required auth scope, and what diagnostics and the summary actually contain. It stops short of describing failure modes (what `ok: false` or missing-frontier cases imply) beyond field names.

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?

Four compact sentences, front-loaded with the action and return shape, then the safety and scope constraints. Dense domain jargon (`bloom:def/`, frontier keys) is used deliberately rather than as filler, though it slightly narrows readability for a newcomer.

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 compensates by naming the returned fields and describing diagnostics and summary contents. Auth scope, read-only semantics and the no-version rule cover what an agent needs before invoking this single-parameter tool.

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?

With schema description coverage at 100% and a single required `branchId`, the schema already carries the parameter meaning, including the note that a check never picks a head automatically. The description reinforces that a single Branch is targeted but adds no format or resolution detail 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 and resource: it compiles one Branch's Project Definition from `bloom:def/` using Bloom's authoritative compiler. The returned shape is spelled out, and no sibling tool (list_branches, read_files, code_search) does anything comparable, so the agent can select this without ambiguity.

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?

Gives clear operating context: read-only, requires the `project:read` scope, never accepts a version, and never changes infrastructure. It does not explicitly name an alternative tool or a when-not-to-use condition, which keeps it below a 5.

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