create_spec

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

With no annotations provided, the description must carry the full behavioral disclosure burden. The word 'immutable' is a useful, non-obvious behavioral trait indicating append-only semantics and that prior versions are not overwritten, and 'Append' reinforces additive behavior. However, the description does not cover error conditions, idempotency, or side effects, so disclosure remains thin.

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?

The description is a single, front-loaded sentence with no filler, repetition, or wasted words. It efficiently communicates the verb, resource, and scope. It could be longer to add behavioral detail, but as a concise structure it is well structured.

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?

The tool has 9 parameters, 2 required, no annotations, and 0% schema coverage, so the description is far too thin for an agent to construct a valid call. It does not explain required parameters, optional field semantics, or how the appended spec version relates to the family lifecycle. The presence of an output schema does not compensate for this absence of input context.

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 description coverage is 0%, so the description should compensate by clarifying parameter meanings. The description only hints at family_id by saying 'for a family' and says nothing about objective, constraints, contract_ids, deliverables, out_of_scope, required_evidence, supersedes_spec_id, or acceptance_criteria. An agent gets almost no parameter-level guidance beyond the schema's property names.

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 description names a concrete action ('Append') and resource ('an immutable specification version') scoped to a family, which broadly distinguishes it from siblings like create_family or create_project. It is clear enough for an agent to understand the core intent, though it does not explicitly call out any sibling alternatives.

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?

There is no guidance about when to use this tool versus alternatives such as create_family, submit_plan, or submit_evidence. It only implies use for a family, but does not state that the family must already exist or that a spec version is being added to an existing family. An agent is left to infer the workflow context.

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