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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered by structured data. The description nevertheless adds genuinely useful behavior: values are never returned, and spending a credential happens server-side via an approved action. It does not cover ordering, limits, or what shape each entry takes beyond having a note, which keeps it at 3-adjacent territory; the added context is real but narrow.

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?

Three short sentences, front-loaded with what is returned before the scoping rules. The telegraphic fragments ('Filter with q.') are efficient, though slightly clipped for a definition that also has to signal the no-values constraint.

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?

There is no output schema, so the description must convey return content, and it does: entries are names with notes explaining purpose, and values are deliberately excluded. With annotations carrying safety and schema carrying parameter detail, nothing material is missing for correct 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 description coverage is 100%, and the description's project_id and q statements largely restate the schema's own wording, including the 'global names' case. The .env analogy adds a little interpretability but no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 uses a concrete resource and qualifier: it returns the credential NAMES a connection can spend, never their values. That is far more specific than the title alone. It doesn't name a sibling tool as the contrasting alternative, so it lands at 4 rather than 5.

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?

It clearly states the two usage modes — with project_id for one project's drawer, without it for every granted project plus globals — and that q filters. That is clear context for when each parameter shape applies. It stops short of explicit exclusions or naming an alternative for retrieving/spending values, so it is not a 5.

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