propose_link

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

With no annotations, the description must carry the full behavioral burden; it does disclose the key trait that the result is a pending proposal routed for review rather than an immediate write to the trace matrix. It says nothing about permissions, duplicate/pending-link handling, idempotency, or what the call returns, so the write path is only partly characterized.

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?

Two tight sentences with no filler; the core action comes first and the queue-vs-matrix distinction follows immediately. Every clause earns its place.

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 a 3-required-param mutation tool with no annotations, no output schema, and zero schema descriptions, the description captures the most important workflow semantics (pending review) but leaves parameter intent and edge-case behavior undocumented. Adequate to route the call, not sufficient to call it confidently.

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 0%, so the description is responsible for parameter meaning, yet it explains none of the three required fields explicitly. 'class implements a requirement' lets an agent infer class_name and requirement_id, but 'reason' is completely unaddressed and no format or constraint hints are given.

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 (propose) and resource (a link between a class and a requirement), and explicitly contrasts the outcome with the sibling trace_matrix. An agent can distinguish it from trace_matrix and related_classes 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?

The clause 'goes to the review queue, not the trace matrix' tells the agent when this tool is the right choice versus trace_matrix. It stops short of stating preconditions (e.g., use only when the link is unverified or does not yet exist) or exclusions for other siblings.

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