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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it discloses that each moved claim gets a journal line grounded in 'reason', that nothing is carried into 'lean', and that the other scale's blocks revert to unread boxes. It does not state irreversibility or what happens if a mapping is incomplete, which keeps it from a 5.

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 and scale vocabularies, then the migration rules, then permissions. Dense but nearly every sentence carries a constraint. Slightly run-on in the mid-section where mapping and journal effects are packed together.

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?

For a destructive, permission-gated configuration tool with no output schema, the description covers side effects, authorization, mapping requirements, and edge cases (lean exclusions, orphaned blocks). An agent has everything needed to call it correctly or to stop and ask a human.

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. The description adds real value: it constrains 'statuses' and 'kinds' to one entry per status/kind in use and gives concrete JSON examples ({"open":"draft"}, {"theorem":"position"}), plus explains that 'reason' becomes the journal ground. It doesn't clarify the 'lean' exclusion at the parameter level, so not a 5.

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?

Opens with a specific verb and resource: 'Choose the scale and kinds a project's claims are written on.' It then enumerates the two scales and their full vocabularies, so an agent knows exactly what domain this operates on and can separate it from siblings like set_claim or set_claim_status.

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?

Explicitly states the free case ('Free while the project has no claims') versus the migration case ('With claims, carry every status and every kind in use...'), names the permission boundary ('its lead or an administrator'), and gives a hard behavioral rule: 'ask the person which goes where, never guess.' When-to-use and constraints are unambiguous.

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