innoslate_apply

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), and the description adds real behavioral detail on top: the dry-run/token confirmation protocol, that every relation is written on both sides, that matching is scoped by number within a document, and that update_existing gates mutation of matched items. It does not describe partial-failure behavior or rate limits, which keeps 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-loaded with the core purpose and the dry-run rule before the example. The plan example is dense but every line demonstrates a distinct field or ref form, so it earns its space; the closing sentences efficiently compress matching, bidirectional relations, and non-deletion. Slightly long, but not padded.

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 complex, nested-input mutation tool with no output schema, the description covers the write semantics, the confirmation gate, matching rules, and deletion behavior. The gaps are project_url and the read-back format, but the dry-run confirmation loop covers the critical path an agent needs to call this safely.

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%, so the description carries the full burden and largely succeeds: it documents the plan's shape (update_existing, entities, relations, unlink), the meaning of key/class/number/document/parent/attributes, and defines what a ref can be. dry_run and confirm_token are explained via the workflow, though project_url is never mentioned and several nested fields are only shown by example rather than explained.

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 pair and resources: 'Create or update entities and relations in one save, then read everything back to verify.' The 'in one save' framing distinguishes it from the sibling innoslate_update, which presumably handles single-item mutations. An agent can tell what this tool does and how it differs from atomic edit tools.

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 an explicit mandatory workflow: always call dry_run=true first, show the summary and confirm_token to the user, and only re-call with identical plan, dry_run=false, plus the token after approval. It also states exclusions implicitly via 'Nothing is deleted' and describes matching scope ('matched by number inside their document only'). This is well beyond minimum guidance.

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