PulseWatch public knowledge

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by clarifying the tool returns static package information and explicitly excludes live capacity and purchase functionality, which is useful behavioral context beyond the annotations.

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 a single, dense sentence that front-loads the core purpose and then adds the key exclusion. Every word earns its place, and the negative scope is concise and informative.

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?

The tool is simple: one optional parameter, no required fields, and an output schema exists. The description covers the content scope and the key exclusions. It doesn't mention the locale parameter, but the schema fully documents it, so nothing critical is missing for an agent to call the tool correctly.

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%, but there is only one optional parameter (locale) with an enum of 'en' and 'hr' and a default of 'en'. The description doesn't mention locale, but the schema fully documents it with enum values and a default, so the parameter semantics are already clear from the schema. Baseline 3 is appropriate.

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 clearly states the tool reads the three public service packages, including prices, scope, conditions, and the written enquiry process. It distinguishes itself from a purchase or live capacity tool, making its purpose unambiguous.

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?

The description implies when to use this tool: when the user needs static public service package information, not live capacity or purchasing. It doesn't explicitly name alternatives, but the negative scope ('Not live capacity or a purchase') provides clear context for when not to use it.

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?

The annotations already cover readOnlyHint, idempotentHint, and destructiveHint, so the description's burden is reduced. It still adds meaningful behavioral context: only catalogue IDs are accepted and URL/file inputs are rejected. However, it does not disclose behavior on missing or invalid IDs, which would be a minor value-add beyond what annotations provide.

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 sentences, front-loaded with the action and the source of the ID, with no filler or redundant restatement. Every phrase earns its place.

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?

Given a single parameter, an output schema, and strong annotations, the description covers the core context: what to pass and what not to pass. It doesn't explicitly describe error behavior for missing documents, but that's supplemented by the output schema and the tool's false; for a read-only, idempotent tool this is adequate.

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 0% schema coverage, the description carries the full burden for the 'id' parameter. It compensates by defining the id precisely: an exact public catalogue ID returned by search_knowledge, and it rejects URLs or file references. This gives the agent enough semantic grounding to populate the parameter correctly, despite lacking a detailed format specification.

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 states a specific operation (read) and resource (a public document by ID returned by search_knowledge), and differentiates it from arbitrary URL/file access. It also implies a contrast with list_offers by requiring an exact ID rather than listing, making the tool's role clear even without opening sibling schemas.

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?

The description gives clear context: use this tool when you have an exact catalogue ID from search_knowledge, and explicitly says not to use it for URLs or file access. It does not name the sibling tools as alternatives, but the conditional guidance is sufficient for an agent to route between them.

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, and non-destructive behavior resume. The description adds valuable behavioral context: results are public sources only, returns URLs and excerpts rather than generated content, and suggests concise query terms. This goes beyond the annotations meaningfully.

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 two sentences with no filler. The core purpose is front-loaded, and the second sentence adds return behavior and practical query guidance in a compact, readable way.

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 and annotations covering side-effect safety, the description provides enough context for a simple search tool. It clarifies the domain, languages, result type, and non-advice boundary. The main gap is lack of explicit routing advice relative to sibling tools, but this is not critical for calling the tool correctly.

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?

Even though schema description coverage is 0%, the description explains the core query semantics ('keywords'), ties the locale to EN or HR, and provides concrete example terms. It does not elaborate on 'limit', but the parameter name plus schema defaults make that reasonably self-explanatory.

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 states a specific verb ('Find'), a specific resource ('public PulseWatch sources'), and the search mechanism (keywords in EN or HR). It also clarifies what the tool returns ('source URLs and excerpts, not generated advice'), which distinguishes it from tools that might produce generated knowledge or offers.

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?

The description gives clear usage context: use it to find public sources by keyword and language, and it explicitly says the result is source links, not generated advice. It does not directly name sibling tools or state when not to use it, but the context is strong enough to guide selection.

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