kb_propose_changes

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

No annotations are provided, so the description carries the full burden, and it delivers: it asserts nothing is written, spells out the return shape (unified diff, create/update/append action per op, before/after verification with warning delta), and flags the index.md rewrite cost. It does not cover permission/auth requirements or failure behavior for malformed ops, keeping it short of 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-loads the single most decision-relevant fact ('Preview a change set without writing'), then the op grammar, then a tie-breaking preference, then the return contract. Every sentence adds information; nothing is redundant boilerplate.

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 and no annotations, the description covers inputs, outputs, and the non-mutating guarantee well. The notable gap is the missing explicit handoff to kb_apply_changes (i.e., that a proposal is what you feed to the apply step), which an agent sequencing multi-step edits would benefit from.

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% and the single parameter is a free-form array of objects with additionalProperties permitted, so the schema explains nothing. The description fully compensates by enumerating the four discriminated op shapes and their required fields (page_id/text, category/entry, etc.), which is exactly the documentation the schema omits.

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 ('Preview a change set') with an explicit scope constraint ('without writing'), which cleanly separates it from kb_apply_changes and the read-only siblings like kb_read_page and kb_verify. An agent can tell what this does without opening the schema.

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 in-tool guidance: 'Prefer add_index_entry for a new page: it adds one catalog line without reading or rewriting index.md,' which steers operation selection. However, it never names kb_apply_changes as the commit counterpart or states when-not to use this tool (e.g., for trivial reads).

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