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

Annotations declare destructiveHint=true and readOnlyHint=false; the description corroborates and explains why — the latest word per declaration is kept, so prior reports are superseded — and adds an authorization constraint ('Members of the project who may write only') plus the exact cleanliness rule (propext/Classical.choice/Quot.sound only, no sorryAx, no project axioms). It does not describe failure modes or what happens when output and declarations disagree.

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?

Purpose is front-loaded, but the single dense paragraph packs multiple clauses with em-dashes, and phrasing like 'as a computation's report is' forces re-reading. Content earns its place, yet it would be clearer as short separated statements.

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 does supply the return shape ('whether it is clean and the claims bound to it') and the upstream data formats, and it states the write permission requirement. Minor gaps remain around conflict handling between the two inputs and error behavior.

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, but the description goes beyond the terse schema field docs by showing the literal Lean output lines and the exact JSON shape for 'declarations'. The interaction semantics ('or both', latest word wins) are supplied here rather than in the schema.

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+resource+scope: reporting what a CI's `#print axioms` said of Lean declarations in one repository at one commit. That clearly separates it from siblings like find_lean_declaration (lookup) and report_computation (a different report kind).

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 concrete invocation guidance: pass Lean's raw output in 'output', structured data in 'declarations', or both, with format examples. It does not state when to prefer this over alternatives or when not to call it, so it falls short of a 5.

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