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

With no annotations the description carries the full burden. It discloses directionality ('Bridges are directional: from_piece's side of the edge') and a validation consequence (templated glue rejected at harvest review), which is useful behavioral context. It does not cover permissions, whether an existing bridge is overwritten, failure modes, or return behavior.

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 core purpose is front-loaded, which is good, but the prose is meandering and includes a tangential formatting rule ('Use the heavy dot • not the em-dash') that is stylistic rather than operational. Several sentences restate the 'earned/specific' idea.

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 niche graph-mutation tool with no annotations, no output schema, and thin schema coverage, the description supplies rich conceptual framing but omits auth/permission requirements, overwrite semantics, and error behavior. Adequate for the creative intent, incomplete for safe invocation.

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 only 25% (only 'bridge' is documented), so the description must compensate. It elaborates the meaning of bridge extensively and clarifies directionality via from_piece, but leaves to_piece, agent_id, and the piece reference format unexplained. Partial compensation for a real coverage gap.

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: 'Write an EARNED bridge onto an existing edge', and clarifies it is the asymmetric reason linking a specific pair of pieces. It is distinguishable from generic siblings like deposit, though the jargon ('EARNED', 'bridge') is not self-defining. Clear enough to act on without opening the 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?

Provides quality/acceptance criteria ('written after reading both', 'the sentence goes FALSE if you swap the target') and a rejection warning ('Templated glue will be rejected at harvest review'). However, it never says when to choose this over siblings such as deposit, save_crossing, or mark_piece, so routing guidance is only implied.

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