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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds only the provenance of the id value, not return format, error behavior, or missing-id handling.

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?

A single tight sentence with the key constraint (one posting, by id from search) front-loaded and zero 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?

An output schema exists, so return values need not be explained. For a one-param lookup with full annotations, the description covers what an agent needs, though a note on missing ids or errors would complete it.

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?

The single parameter has 0% schema description coverage, so the description must carry the meaning. "id returned from search" usefully tells the agent where the id originates, but gives no format or validation details.

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 (Fetch) and resource (one posting) with a clear singular scope. It implicitly distinguishes itself from the search sibling by noting the id comes from search, but never names the alternative 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?

"the id returned from search" implies this is a follow-up call to search, which is useful sequencing context. However, there is no explicit when-to-use/when-not guidance or named alternative to route the agent.

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, idempotentHint, openWorldHint, and destructiveHint=false. The description adds useful context beyond those annotations: it explains that verification is performed via a one-result search because 'Reed has no account endpoint.' That is genuine behavioral disclosure about the underlying mechanism.

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 purpose. The implementation note is parenthetical and brief. No wasted words.

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 a rich output schema and full annotations, the description need not explain return values or safety. It covers purpose and the underlying verification approach. The main gap is the absence of usage guidelines relative to sibling tools.

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?

The tool takes zero parameters, so the baseline is 4. Schema description coverage is 100%, and there are no parameters to document further.

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 clear verb and resource: 'Verify the credentials and describe the connected account.' This is specific enough for an agent to know it's an identity/account check, distinct from get_posting and search, though it does not explicitly name or contrast those siblings.

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 phrase 'Verify the credentials' implies a use case, but there is no explicit when-to-use guidance, no when-not-to-use conditions, and no mention of alternatives like search or get_posting. Usage is only implied.

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, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is fully covered. The one added claim ('normalised postings plus the raw record') describes return shape, which the output schema already carries, and there is no mention of pagination interplay, rate limits, or auth. It adds almost nothing beyond structured fields.

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 and the core purpose is front-loaded with zero filler. Brevity is good, though it is arguably terse to the point of under-specifying a 7-parameter tool.

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 tool with 7 parameters and three siblings, one sentence is not enough: no usage routing, no mention of filters, no pagination guidance, and an ambiguous reference to 'the platform'. It leans on the output schema and annotations to carry the weight but still leaves gaps an agent must guess at.

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?

Seven parameters with only 71% schema description coverage; 'remote' and 'location' are undocumented anywhere. The description offers no parameter guidance at all — no filter semantics, no cursor-vs-page advice. Since coverage is below the 80% baseline and the description does not compensate, it scores low.

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+resource: 'Search the platform's job postings.' An agent knows it queries postings rather than fetching one. It does not distinguish itself from get_posting or explain what 'the platform' is, so it falls short of a 5.

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?

No when-to-use statement and no reference to alternatives. With siblings me and get_posting, the description never says to use search for discovery and get_posting for retrieval by identifier. The division of labour is left entirely to inference.

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