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

With no annotations provided, the description carries the full burden — and it excels. It discloses precise edge-case semantics: UTC-calendar day is end-inclusive while ISO instants impose an exclusive upper bound, status is set-membership matched, sent_hour matches local wall-hour in a timezone, and page is 0-indexed. It also reveals the filter-reflected total behavior in the return contract — substantive behavioral detail far beyond what structured fields could convey.

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?

The description is front-loaded with an excellent one-sentence summary before diving into parameter details, and every sentence earns its place given the tool's complexity. However, the body is a dense wall-of-text with minor grammatical slips ('Bound the date_field column' should be 'Bounds...'), and the sent_hour sentence crams three clauses into one long construction.

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 14-parameter tool with zero annotations and minimal schema help, the description is remarkably complete: it covers defaults, allowed values, edge cases, timezone behavior, and result shape across all meaningful dimensions. The output schema existing means the return value explanation is unnecessary. Minor deduction for the unaddressed dpop_token parameter and silence on pagination edge cases (e.g., behavior past the last page).

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?

With schema coverage at a paltry 7% (only npub documented), the description carries the entire semantic burden and succeeds admirably. It explains 12 of 14 parameters with exact allowed values (created|updated|status|scheduled), defaults, validation constraints (page_size 1..100, sent_hour 0-23), date-format disambiguation (bare YYYY-MM-DD vs ISO instant), and matching rules (regex, set membership, wall-hour equality). Only dpop_token is left undocumented in both schema and prose.

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 opening sentence — 'List your stored posts, server-side sorted, filtered, and offset-paginated' — uses a specific verb+resource and clearly scopes the tool to user posts with rich server-side processing. It implicitly distinguishes itself from sibling list tools (list_coupons, list_snippets, list_notarizations) by resource type, though it never explicitly names alternatives or contrasts itself the way the get_calls example does.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tools are named (e.g., nothing like 'for a single post, use get_post'). However, the extensive parameter semantics strongly imply the tool's use cases (time-of-day deep-links, template filtering, date-range queries), giving clear contextual usage context without ever stating exclusions or alternatives.

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