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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description doesn't need to argue safety. It does add value annotations don't carry: the default filter is live-only, and each entry reports who, tool, model, state and last-active. It stops short of anything a caller might want to know about ordering or what 'stale' means operationally.

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?

A single sentence plus a scope clause, no filler, and the staleness caveat is placed last where it reads as a modifier. It is slightly telegraphic — the field list ('who, tool and model, state, last active') is compressed near the limit of parseability.

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?

With no output schema, describing the per-session fields is the right call and it does so. For a 3-parameter, read-only list tool this is close to sufficient; the remaining gap is ordering/pagination behavior and what qualifies a session as stale, neither of which is disclosed anywhere.

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 100%, so repo, limit and include_stale are already documented, and the description mostly restates include_stale. Its only genuine addition is disclosing the default live-only filtering behavior, which the schema alone does not make explicit. That is above the baseline but not by much.

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 names a specific resource (agent sessions on a repository) and the payload (the issues each holds, plus who/tool/model/state/last active). It is clear what is returned, but it never distinguishes itself from nearby siblings such as who_holds or needs_you, which plausibly surface overlapping session/ownership data.

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?

Usage is only implied: the agent can infer this is the tool for enumerating active agent sessions, and the include_stale clause hints at the live-vs-parked distinction. There is no explicit when-to-use, no prerequisites (e.g. token scope covering multiple repos), and no pointer to an alternative when what is wanted is ownership or attention data.

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