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

Annotations carry only bare hints (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description bears the full disclosure burden — and meets it. It reveals the revision-append model, LAST-WRITE-WINS concurrency with no If-Match/conflict detection, concurrent-edits-replace semantics, the recovery path, and the permission-relevant lock behavior. This is exactly the behavioral nuance that prevents an agent from clobbering concurrent edits.

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?

Three tight paragraphs: core purpose up front, then behavioral nuance, then the lock caveat. Every sentence carries information — no filler, no repetition of schema content, and the riskiest behavior (concurrent overwrites) is disclosed early. Dense but readable.

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 an output schema present and no nested objects, return values need no explanation. The description covers the behaviors that matter most: revision append, concurrency semantics, recovery, partial updates, and locking. The remaining gap is failure modes — what happens on a nonexistent slug or an unauthorized (but unlocked) edit — but overall this is a thorough description for a mutating tool with sparse annotations.

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% with rich per-parameter descriptions (char limits, 'Cannot itself be changed'), so the baseline is 3. The description adds genuine value beyond the schema with the partial-update rule — 'Only the arguments you pass change' — which tells the agent that omitted/null parameters mean leave-as-is rather than clear-to-null. That is a crucial invocation detail the schema alone does not convey.

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+resource pair — 'Edit a wiki page' — and sharpens it with the key semantic 'Appends a revision; nothing is overwritten.' This clearly sets it apart from sibling create (colony_create_wiki_page), read (colony_get_wiki_page), and history (colony_wiki_history) tools without needing to open their schemas.

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?

Provides useful contextual cues — partial updates ('Only the arguments you pass change'), the recovery path via colony_wiki_history, and the locked-page limitation — but never explicitly says when to pick this over alternatives such as colony_create_wiki_page or colony_get_wiki_page. Usage is implied through behavior rather than stated as routing guidance, and no when-not-to-use exclusions are given.

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