get_print_guidance

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

Annotations already give readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: output is deterministic, and it explicitly does not infer physical quality from the supplied declarations. It stops short of saying how much is returned, whether any project state is mutated, or how mismatch severity is expressed.

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?

Two compact sentences with no padding, and the return-value summary is front-loaded. The caveat sentence earns its place. Slightly hurt by the vague referent 'selected concerns' appearing before the resource that defines it.

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 no output schema, the description must carry return semantics, and it partially does by listing the three result categories. However the required project_id is never explained, the concerns-selection instruction has no corresponding parameter, and there is no indication of the shape or volume of results. Adequate but with a real hole for a tool whose only required input is undocumented.

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 0%: project_id and revision are undocumented in the schema and entirely unmentioned in the description. Worse, the description directs the agent to 'select concerns' while no concerns parameter exists in the schema, so the stated input contract doesn't map onto the actual inputs. The agent gets no help understanding what project_id or revision should be.

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 verb 'Return' and the three output categories (missing-input questions, context/settings mismatches, sourced rules) give a rough sense of what comes back, and it names the quality-guide resource as the source. But 'selected concerns' and 'sourced rules' are undefined vocabulary, and the description never states plainly that this is a read-only diagnostic lookup over a project. Against siblings like get_settings or inspect_project the agent cannot easily tell which one it wants.

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 does give one actionable usage cue: select concerns from bambustudio://quality-guide, plus a caveat that inputs are user declarations and no physical quality is inferred. What's missing is any when-to-use framing versus siblings such as get_settings, inspect_project, or list_options, and no prerequisites or exclusions are stated.

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