bulk_update_records

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

Goes well beyond the annotations (which only cover destructive/idempotent/openWorld) by disclosing Id format-checking timing and its per-row failure blast radius for CSV, the #N/A null write that clears a field, the >500-row user confirmation gate, and the fact that a partially completed job returns jobId/state rather than blocking. These are exactly the non-obvious traits an agent needs before mutating data.

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 operation and mechanism, then layers constraints, failure semantics, and return shape in a tight sequence of short sentences. No filler and no repetition of the title.

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 correctly summarizes the return payload (jobId, state, processed/failed counts, sample failures) and explains the 'wait' cutoff behavior. Combined with the input-mode routing rules and destructive-write semantics, an agent has everything needed to call this correctly.

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?

With reported schema coverage at 0% for the nested input object, the description carries real weight: it adds the critical constraint that every record/CSV row must include 'Id' and that only provided fields are changed, neither of which is enforced by the schema. It partly duplicates schema text ('exactly one of records/csvPath/csvContent', 'null clears a field'), so it is not purely additive, but the Id requirement is a genuine gap-filler.

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+mechanism: 'Update many existing records by Id with the Bulk API 2.0.' This clearly separates it from bulk_insert_records, bulk_upsert_records and single-record update_record without needing to open any 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 an explicit routing rule for the input modes ('Provide exactly one of records, csvPath or csvContent') and names the alternative when the wrong one is chosen ('If the file was uploaded into a sandboxed client, use csvContent instead'). It does not explicitly state when to prefer this over the sibling update_record (single record) or bulk_upsert_records (matching on external Id), so the tool-level exclusion is only implied by 'many existing records by Id'.

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