Remember Me Collections

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, non-open-world), so the description is free to add behavior instead of repeating it. It does: unlisted collections are silently excluded from results, and each result's `image` is the raw stored publisher URL (possibly null) rather than the computed display image. That field-semantics disclosure is genuinely useful, though no pagination edge behavior or result-size limits are discussed.

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, followed by usage, exclusions, result semantics, then an Args block — a sensible order with no wasted sentences. The image/cover paragraph is the longest and slightly verbose for its value, but it is not filler.

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?

All five optional parameters are documented despite 0% schema coverage, annotations already carry the safety profile, and an output schema exists so return values needn't be spelled out — the extra note on the `image` field is bonus rather than a gap. Nothing an agent needs to call this correctly is missing.

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 0%, so the description carries the full burden and does so: it documents search scope (name/description/publisher name), language as a code prefix with examples, the ordering enum with default (-downloads, -created, name), and the limit range 1-100 with default 20. This is meaning well beyond the bare types in the schema.

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 and resource ('Browse published Bible verse collections') plus the three affordances (search, filter, sort). It also distinguishes itself from the sibling get_collection_detail by naming it as the path for unlisted collections, so an agent can route without opening either 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 when-to-use triggers (finding verses to memorize on a theme like hope/anxiety/forgiveness, or a ready-made memory list for a church group) and an explicit exclusion with the alternative named: collections with `listed` false are not returned, but get_collection_detail opens them by id.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds real value beyond them: it explains that the raw `image` is the publisher-stored URL (null when unset, even though a generated cover may display) and that values round-trip with create_collection/add_verse on the authenticated server. It omits any note on item limits, pagination, or read-side auth.

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 in the first sentence and the image caveat follows in a compact block. The image explanation is slightly repetitive (stored vs computed display image stated twice) but each sentence carries information an agent would otherwise guess wrong.

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 an output schema present, return shape need not be described, and the description focuses on the one genuinely non-obvious field (raw image semantics) plus the parameter source. Nothing critical to calling it is missing, though it stays silent on scale/pagination of returned verses.

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 0%, so the description must carry the parameter — and it does, defining collection_id as 'The collection ID (from browse_collections results)', which adds provenance the bare integer schema lacks. It does not specify ID format or validity behavior, so it is not fully compensating.

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 and resource with scope: 'Get full details of a published collection including all verse text, references, and topics.' This implicitly separates it from browse_collections (list-level) and get_collection_metrics (aggregates), though it never names those siblings explicitly.

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 implied rather than stated — the note that collection_id comes 'from browse_collections results' sketches a browse-then-detail workflow, but there is no explicit when-to-use, when-not, or named alternative. Adequate but leaves the agent to infer the routing.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered by structured data. The description adds the metric content but says nothing about permissions, result size, or time-window of the stats, which is the remaining behavioral gap for a metrics endpoint.

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?

Two compact parts: a front-loaded purpose sentence listing the metrics, then a short Args block. No filler, though the Args line mostly restates a parameter already visible in the schema.

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 single-parameter, read-only tool with an output schema present, the description covers purpose, return content families, and parameter provenance — enough to invoke correctly. The only omission is guidance against the sibling get_collection_detail.

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 0%, so the description must carry the single parameter, and it does add real value by stating where collection_id comes from (browse_collections results). It does not restate the integer type or validity constraints, so it is not fully compensating, but for one parameter this is close to adequate.

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 verb ('Get') and resource ('community engagement metrics') and enumerates the metric families returned (memorization progress, verse mastery, difficult verses, activity stats), so the agent knows exactly what it retrieves. It does not explicitly contrast itself with get_collection_detail or browse_collections, so sibling differentiation is left implicit.

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: it is a read of metrics for one collection, and the arg note 'from browse_collections results' hints at the workflow that produces the ID. There is no statement of when to prefer this over get_collection_detail, which is the most likely confusion given the sibling list.

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