entity_record

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

Beyond the annotations (readOnly=false, destructive=false), the description discloses real behavior: duplicate words are merged into the existing Statement as further evidence, USER_WORDS_PROTECTED and USER_CONFIRMATION_REQUIRED constrain what can be superseded or restored, and expectedVersion is an optimistic-concurrency token. With no output schema, it also spells out the return shape {entityId, version, accountId, added?, merged?, changed?, supported?}.

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?

It is one dense paragraph with no structure, and several clauses restate what the schema already says (aliases as the complete list, update fields, sensitivity behavior). The purpose is front-loaded correctly and most sentences carry non-obvious rules, but the wall of text makes the protected-statement and versioning rules easy to miss.

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 write tool with no output schema, the description covers the important ground: merge semantics, protection rules, concurrency, verbatim requirements, and the response shape. Gaps remain around when to prefer sibling recording tools and around parameters like name and via, but nothing critical for a correct call is missing.

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 73%, and the description adds genuine meaning on top: aliases is the complete replacement list, add can supersede or conflict and carries a basis for inference, update covers status/reason/sensitivity/inSummary, and expectedVersion must come from the last read or write. It also states the verbatim rule for text. One flaw: it refers to 'accountText', which does not exist in the schema (the field is accountSource), and name and via get no semantic help.

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?

The opening sentence states a specific verb and resource: record the user's words about an Entity together with the changes they make (name, aliases, add, update, support). This is a precise write operation, and the required entityId plus versioning makes it implicitly distinguishable from entity_create. It never names a sibling tool explicitly, so differentiation from event_note or entity_create is left to inference.

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?

It gives situational guidance for the protected-statement case (add your version with conflictsWith instead of superseding the user's words) and for disputed statements (USER_CONFIRMATION_REQUIRED). However, it never states when to call this versus entity_create, event_note, or event_record_expression, and there are no explicit exclusions. Usage is implied by the parameter contract rather than stated.

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