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

Annotations already declare the safe read profile (readOnly, idempotent, non-destructive), so the description is not needed for safety. It does add genuine behavioral context by explaining that 'Current means the references still match; it is not approval or proof validity', which prevents the agent from misreading a status value as an approval. It omits pagination and return-shape 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?

Two sentences, front-loaded with the core operation, and the semantic caveat about 'Current' follows economically. No filler, though it is terse enough that it could have absorbed a little more useful detail without bloat.

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 list-style read with no output schema and no other documentation, the description covers purpose and the key status caveat but does not explain what the returned links contain or how paging behaves. The safety profile is carried by annotations, but the return-side picture remains thin.

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 33% (only projectId is described), so the description would ideally compensate, but it says nothing about projectId or the limit/offset paging controls. The two undocumented parameters are self-evident standard pagination fields, which keeps this at a baseline 3 rather than lower.

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: 'Read proposed evidence-to-requirement links', which pins down both the operation and the object. It distinguishes itself from mutation siblings like link_evidence and from the separate read sibling read_evidence_review, but it does not name those siblings explicitly.

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?

No guidance on when to reach for this tool versus link_evidence (the write path) or read_evidence_review (the review-oriented read). The description only clarifies the meaning of the 'Current' state, which is output interpretation, not usage direction.

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