PromptingCraft Guidance

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

Goes well past the annotations by enumerating all four status values with their meanings, disclosing cache TTLs (15 min, 1 min when unavailable), describing rate-limit degradation to status=unavailable with reason=rate_limited, and stating that publication/update dates are never inferred and always null. These are exactly the behaviors readOnly/idempotent hints cannot 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?

Purpose comes first, then status semantics, then caching/rate-limit behavior, then the hard input restriction. Every sentence carries operational information; nothing is restated from the annotations or 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?

An output schema exists, so return structure needn't be re-explained, yet the description still covers the non-obvious parts an agent would misread: null dates, cached vs live fields, and rate-limit-driven unavailability. Nothing needed to invoke or interpret it 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 coverage is 100% and the enum itself lists valid ids, so the schema already does most of the work. The description adds a real constraint beyond the schema: only registry source ids are accepted and no other URL can be requested, which prevents an agent from passing a URL.

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 precise verb and resource: fetch one allowlisted registry page and diff its normalized text against a verified snapshot. The scope (registry-only, no arbitrary URLs) makes it clearly distinct from the get_guidance/search_guidance siblings that supply the ids.

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 reader infers this is the tool for verifying whether a previously retrieved source changed. There is no explicit 'use this when / don't use this when' and no routing to the siblings, though the schema note ties source ids back to search_guidance/get_guidance results.

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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered; the description still adds value by disclosing the error behavior for unknown ids and confirming no network fetch. The enumeration of returned fields is largely redundant with the output schema, so it stops short of a 5.

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 tight sentences, front-loaded with the action and id provenance, with error and no-web-fetch caveats trailing. The field list (provider, URL, applicability, limitations, labels, verified date, hash, commit) is somewhat long and duplicates the output schema, costing a point.

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 one required, fully-described parameter, an output schema, and rich annotations, the description covers the remaining gaps: id provenance and unknown-id error behavior. Nothing an agent needs to invoke it correctly is missing, though the return-field recital is redundant given the output schema.

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% with a pattern and example already present, so the baseline is 3; the description earns the extra point by telling the agent where to obtain the id (from search_guidance), which is semantics the schema cannot express.

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 ("Return one curated record by its stable id") and immediately differentiates itself from the sibling search_guidance by positioning this as the id-based fetch, not the lookup. An agent can pick between get_guidance and search_guidance without inspecting 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?

Explicitly says ids come from search_guidance, states the failure mode for unknown ids, and rules out the web-fetch alternative ("nothing is fetched from the web"). The when-to-use chain and the exclusion are both present.

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 safe read-only, idempotent, non-destructive behavior, while the description adds useful context about returned source types, labels, applicability, verified dates, and the fact that PromptingCraft methodology records are never official provider guidance. Pagination and ordering are not described, but the output schema and limit parameter reduce the need.

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 front-loads the purpose, then adds return scope, a key caveat, and the full-record alternative in compact sentences. There is no filler, and each sentence contributes to tool selection or interpretation.

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 search/list tool with all-optional enum parameters and an output schema, the description covers purpose, return scope, key source caveat, and the full-record alternative. The omission of explicit routing to check_source_freshness is minor given the mention of verified dates.

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 100%, so the baseline is 3; the description adds a meaningful constraint that PromptingCraft methodology records are returned only when kind is promptingcraft_methodology and are never official guidance. It otherwise mostly reinforces the fixed-category enums rather than adding detailed per-parameter semantics.

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 uses a specific verb and resource: 'List curated guidance records' with target agent, model family, scope, and topic matching. It also distinguishes itself from get_guidance by directing full-record retrieval there, so an agent can identify the tool 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?

It explicitly points to get_guidance for full records and states the special kind condition for PromptingCraft methodology records. However, it does not address when to prefer check_source_freshness, so it stops short of full when/when-not/alternatives guidance.

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