Waypoint Reference

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuinely new context by enumerating what is explicitly out of reach (URLs, files, conversations, private records), which sharpens the closed-world boundary beyond openWorldHint=false alone.

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 short sentences, front-loaded with the action and followed by the access boundary; no filler. The second sentence earns its place as a real constraint, though the first sentence's phrasing is slightly muddled.

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 2-parameter read tool with no output schema and no annotation gaps, the description covers what can be retrieved and what cannot. It is thin on the return shape (single item vs. list, row schema contents) and on the slug semantics, which leaves an agent with open questions before calling.

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 compensate. It partially does by hinting at what each `kind` value returns (documentation = authored guide, dataset = synthetic fixture and row schema), but it says nothing about the `slug` identifier, its format, or lookup failure behavior.

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 gives a verb (Read) and a scope (one resource) and implicitly maps the two `kind` values to 'authored guide' and 'complete synthetic fixture and row schema', which is useful. However, 'resource' is generic and the phrase 'complete synthetic fixture and row schema' is ambiguous, and there is no differentiation from the siblings search_reference and validate_records.

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 statement of when to use this tool versus search_reference or validate_records. The only guidance is a negative scope limit (no URLs, files, conversations, or private records), which is a boundary rather than usage direction.

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, non-destructive, closed-world behavior, so the bar is lower. The description adds real value beyond them: it identifies the corpus (authored guides and synthetic fixtures) and discloses that query text is processed transiently, which is meaningful privacy context for a search tool.

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 short, front-loaded sentences with no filler; the core action leads and the safety caveat follows. Nothing is redundant, though the sentences are somewhat disjoint in focus.

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 two-parameter read-only search with no output schema, the description covers corpus and safety but omits return shape, result ordering, and the significance of the limit cap. It is adequate but leaves clear gaps for an agent wanting to use it well.

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% and the description adds nothing about the two parameters. It never explains that query is a free-text string of minLength 1, nor that limit defaults to 5 and is hard-capped at 5 — a non-obvious constraint the agent would benefit from knowing.

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 ('Search') and resource ('authored Waypoint Reference guides and synthetic fixtures'), which is unambiguous. Its siblings (get_resource, validate_records) are different verbs, so confusion is unlikely, though the description never explicitly contrasts itself with them.

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 when-to-use guidance or named alternative; the agent must infer that searching is appropriate over fetching (get_resource) or validating (validate_records). The 'do not send secrets' line is a constraint, not routing guidance.

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/non-destructive, and the description goes well beyond them by disclosing that rows are transient and not persisted, that referential and lifecycle integrity are NOT checked, and that confidential data is prohibited. Those are non-obvious behavioral traits an agent could not infer from the annotations. No contradiction with readOnlyHint=true.

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 tight sentences, front-loaded with the core action and constraint; each sentence adds a distinct limit or caveat. No filler, though the 'one fixed Waypoint schema' phrasing introduces avoidable ambiguity.

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 no output schema, the description should hint at what a validation result contains (errors, row indices, pass/fail), which it omits. It is otherwise adequate about scope and limits for a two-parameter read-only tool.

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 burden, yet it only restates the 20-row cap (already in maxItems) and says nothing about what the three dataset enum values mean or how they relate to the validation schema. The 'one fixed schema' wording even obscures the multi-dataset parameter.

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?

Specific verb (Validate) plus resource (synthetic example rows) and scope (up to 20, against a schema). It is easily distinguishable from get_resource and search_reference. The phrase 'one fixed Waypoint schema' is slightly at odds with the dataset enum of three values, which blurs the purpose a little.

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 real usage boundaries: max 20 rows, transient/non-stored, no foreign-key or lifecycle checks, and a confidentiality caveat. However it never names an alternative tool or states positively when to prefer this over sibling lookups.

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