Update Metadata Record

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

Goes well beyond the annotations (readOnly=false, destructive=true, idempotent=true) by disclosing the write mechanism (through the record's form), a read-back-and-capture verification step, three categories of refused targets, and a permission-dependent restriction on writing scripts or switching on script-bearing records.

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 action and mechanism, followed by refusal rules in one dense but scannable block. No filler, though the final clause about script-writing is long and packs several distinct conditions into one sentence.

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 an 11-parameter, nested-object mutation tool with no output schema, the description covers mechanism, verification, refusal boundaries, and a permission gate. An agent could call this correctly, though it does not explain what the read-back returns or how partial field failures surface.

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%, so the schema already documents all 11 parameters, including update_set's role. The description adds only marginal framing — that the capture is verified in the update set and that fields not on the form are refused — which is largely restated in the schema's fields description. Baseline 3 applies when the schema does the heavy lifting.

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: 'Change fields of application metadata', implemented by writing through the record's form in a named application and update set. It also distinguishes itself from the ACL tools explicitly. It does not, however, distinguish itself from near-siblings like insert_metadata_record, query_update_records, or batch_update_records, so the agent must infer that this one edits one existing record by sys_id.

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 concrete negative guidance: refuses protected files, platform schema tables, and access controls, redirecting ACL work to 'the ACL tools'. It also states a session precondition for code writes. What is missing is positive routing — when to choose this over query_update_records or batch_update_records — but the exclusions are genuinely useful.

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