Log communication history

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

Annotations only say this is a non-destructive write; the description supplies the non-obvious implementation behavior an agent cannot infer: the record is really a back-dated maintenance report, defaults to type 'Other', is created closed, and is deliberately not shared with tenants. It also names the read paths (list_communications/get_communication) where the record surfaces with the original date.

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 what it does, then the storage mechanism, then the read path and the file_email companion. Dense and mostly waste-free, though the '(issue #3)' tracker reference and the long parenthetical add noise an agent does not need.

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 and 10 parameters, so the description has to cover the write's side effects and visibility, which it does (not shared with tenants, appears in list_communications with the original date). Minor gaps remain around the confirm/approval flow and tenant linking, which are only gestured at in the schema.

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 only 40% schema description coverage across 10 parameters, the description carries real load and does explain the mapping semantics (date, counterparties and summary get embedded into the report description; maintenanceType defaults to 'Other'; status is closed). However it says nothing about confirm, tenantIds, propertyId, subject or channel, so the documentation gap is only partly closed. Minimum-viable, not compensating fully.

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 precise verb+resource ('Record a past email thread, call or letter against a property') and immediately distinguishes itself from the surrounding communication tools by explaining that Lendlord has no generic communication log. An agent can tell this apart from add_communication_message, create_maintenance_report and file_email without opening a 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 companion recommendation ('Use file_email as well to keep the full message and attachments'), which tells the agent this tool is not a substitute for document filing. It stops short of stating when NOT to use it (e.g. vs. add_communication_message for live tenant threads), so it is clear context without full exclusions.

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