Patch crawl

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

The annotations already disclose the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), so the description only needs to add context. It does add real value by stating that tags are "Replacement" (overwrite rather than append) and that crawl_action is sent on the wire as "action", but it is silent on what a null field does, whether the patch is partial or full, and what errors occur on an invalid status.

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?

The summary sentence is front-loaded and each Args line is short and single-purpose. The Args block largely mirrors the schema property names, which is mild duplication, but nothing is padded or rhetorical.

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 mutation endpoint with six parameters, zero schema descriptions, no enums, and no output schema, the definition leaves out the information an agent most needs: valid status values, valid crawl_action values, and what the patch returns or how failures surface. The reader knows the shape of the call but not the legal domain, which is a significant gap at this complexity level.

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 description coverage is 0%, so the description must carry all parameter meaning, and it does name and gloss all six: crawl_id, crawl_action (with the wire field name "action"), status, retry_at (ISO 8601 date-time format), tags (list, replacement semantics), and tags_str (comma-separated replacement form). The main gap is that no legal values are given for status or crawl_action and the tags-vs-tags_str precedence is unstated, keeping it below 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?

"Update a crawl: change status, reschedule, retag, or run an action" gives a specific verb plus resource and enumerates the four capabilities. Combined with the PATCH path, an agent can tell this apart from get_crawl, delete_crawl, and create_crawl without opening the schema. It does not explicitly distinguish itself from the sibling patch_snapshot/patch_archiveresult tools, but the resource name (crawl) makes the scope unambiguous.

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?

Usage is only implied: the verb list suggests when each field would be supplied, but there is no statement of prerequisites, no guidance on reading a crawl first, and no explanation of when to use crawl_action versus setting status directly. Since only crawl_id is required and the other five params default to null, the agent gets no help on whether a partial update is safe or which fields combine meaningfully.

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