Find Capacities Objects

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

With no annotations, the description carries the full load and does so thoroughly: per-call budgets (5 relation filters, 45 requests), fallback behavior (a 50-result title search lists the whole type), ordering rules (date-in-title, newest first, undated last), and rate-window notes on fetch_cap. It even discloses partial-result signaling — the "Note:" line plus `seed_complete`/`candidates_complete` — which an agent cannot get from any structured field.

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?

Purpose is front-loaded and nearly every clause carries operational detail. The cost is a dense wall of run-on sentences with repeated defaults (page_budget/fetch_cap limits already in the schema), which makes it harder to scan than a bulleted form would be.

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 an 8-parameter tool with nested filter objects, no annotations, and no output schema, the description covers staging, budget exhaustion, result ordering, and even the shape of the second text block. An agent has everything needed to call it correctly and to interpret an incomplete result.

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 adds real meaning beyond it: title matching ignores case/accents/punctuation, requires a letter or digit, and short numeric hints match dates ("1:1" matches 2024-11-12). It also explains how page_budget and fetch_cap interact with the 45-request budget rather than just restating their defaults.

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?

Opens with a concrete verb+resource and scope: "Locate objects of one `structure`... then filter and sort client-side on properties the API cannot search." It also implicitly separates itself from body-returning siblings by stating it returns ids+titles only, so an agent can tell it apart from get_object without opening the schema.

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?

Gives explicit seeding strategies (title_hint, tag, both, neither) with the condition for each ("omit `title_hint` to list by tag or list the whole type") and routes to get_object for bodies and get_space_info for structure ids. The one gap is that the overlapping full-text sibling search_content is never mentioned, so the choice between property-filtering here versus content search must be inferred.

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