agy_project_link

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

Goes well beyond the annotations (which only say readOnly=false, destructive=false, openWorld=false): the binding is declared immutable and non-cross-project, and 'No model call' plus the on_demand clause explicitly rule out starting turns/loops or bypassing client approvals, CLI limits and cancellation. Spent-attempt and checkpoint/provenance behavior is also disclosed. Minor gap: no failure or conflict behavior described.

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 purpose is front-loaded, but the body is a dense semicolon-chained run-on that mixes the core action, parameter semantics, memory-checkpoint behavior, and an apparently unrelated 'Save exact legacy snapshot before paging' instruction. Several clauses (legacy snapshot, paging) seem off-topic for a link operation and dilute the actionable content.

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 five-parameter mutation with no output schema and only safety annotations, the description covers a lot of behavioral ground (immutability, no model call, on_demand effects). It is incomplete on expected_version concurrency semantics and reason, and leaves the 'legacy snapshot before paging' clause unexplained, so an agent still lacks what it needs to call this correctly under conflict.

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% across five parameters, so the description must carry the burden. It explains on_demand thoroughly (default true, no lifetime round budget, no loop start) and implies project_id/discussion_id, but expected_version and reason are never mentioned at all — critical omissions for a versioned mutation and an audit field.

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 gives a specific verb and both resources: 'Explicitly link a local discussion to one lasting project.' The immutability and non-cross-project constraint further narrows it, distinguishing it from siblings like agy_project_update or agy_discussion_create. It stops short of naming those siblings, so an agent must infer the boundary.

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?

'Create a new normal discussion and link it to reuse the project across topics/sessions; archived discussions stay archived' implies the reuse scenario but never explicitly states when-not to call it or names an alternative tool. The prerequisite 'Save exact legacy snapshot before paging' is a usage-ordering hint, though its relevance to this tool is unexplained.

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