raynet_update_record

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses that only VERIFIED fields are editable, that phase changes are a manual override against an automated follow-up system that may re-adjust later, that description fields OVERWRITE rather than append, and that lost-status editing is impossible via the API. These are exactly the non-obvious side effects an agent must know.

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 core purpose and stays on task across four sentences, but the final sentence is long and does some redundant re-litigating of the 'lost' limitation with parenthetical justification ('confirmed against Raynet's own API spec, not just live testing'). Slightly more than needed, though nothing is wasted conceptually.

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?

No output schema exists, and the description adequately implies success semantics by instructing the agent to warn the user after a successful phase change. For a 5-param mutation tool it covers permissions-free but consequence-heavy behavior well; only the exact return shape of a successful update is unaddressed.

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 per the rubric the baseline is 3. The description adds some value by flagging the overwrite semantics of description and the exact-match requirement for business_case_phase, but most of that detail already lives in the schema field descriptions, and it defers field specifics to 'see each field's description'.

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 ('Updates a field on an existing lead or businessCase record') and scopes exactly which entities are in play. An agent can immediately separate it from raynet_create_lead_full, raynet_delete_record, and raynet_convert_lead_to_bc without opening 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?

Goes beyond plain when-to-use: it names the sibling discovery tools (raynet_get_bc_phases, raynet_get_enumerations) needed to supply valid phase values, and explicitly states when NOT to use it (marking a BC 'lost' is unsupported and must be done in the Raynet UI). Conditions and exclusions are both covered.

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