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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the default page size of 20, the 100 cap, cross-gym aggregation by default, and the fields returned. It stops short of saying what happens when the cap is hit (truncation vs. pagination), which matters for a capped list.

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 front-loaded sentences of trigger, behavior and exclusion, with no filler. The parenthetical '(20 by default)' sits well next to the cap, though sentence two crams default size, scope, return fields and optional filtering into one long clause that could be split for scanability.

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?

Output schema exists, so return values needn't be explained, and the description nonetheless names the key fields. For a read-only capped list tool, what's missing is only the truncation/pagination behavior at the 100 limit and how to page past it — a modest gap rather than a blocker.

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 the baseline is 3, but the description reinforces limit semantics ('up to 100 members (20 by default)') and the name-match behavior of search ('only those whose name matches'), which is a slight gloss over the schema's contains-words-in-any-order, accent-insensitive rule. It doesn't mention gymId scoping explicitly beyond 'across all the user's gyms or one'.

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+resource (list members) with scope (all the user's gyms or one) and the returned fields (id, name, gym, last edit time). It also explicitly distinguishes itself from a sibling-style capability by excluding email, phone and notes, so an agent can tell it apart from member-detail lookups.

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?

Opens with an explicit trigger ('Use this when someone asks who their members are, or needs a member's id to book them, update their details or look up their sessions'), naming the downstream tools (book_appointment, update_member, session listing) that require an id from here. It also states a clear exclusion: not for email, phone or notes.

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