agent-crm

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds meaningful behavioral detail by specifying the return content: matching jobs, their status levels, supporting tests, and an explicit negative answer when unsupported. No contradiction with 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, front-loaded sentence that packs purpose, scope, and output details without wasted words. Every clause contributes useful information.

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 appropriately explains the return values (statuses, tests, explicit unsupported answer). It is complete for a low-complexity lookup tool with strong annotations, though it omits minor details like limit behavior.

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 50%: query has a description, limit does not. The description reinforces the query semantics ('can this framework do X?') but does not explain the limit parameter. It adds some meaning beyond the schema but does not fully compensate for the undocumented limit.

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 ('Answer') and names a precise resource ('CRM jobs-to-be-done index'), clearly distinguishing this from sibling tools like get_capability and search_docs. It also explains the output categories, making the tool's 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 clearly states when to use the tool: when the user asks 'can this framework do X?'. It does not explicitly mention alternatives or exclusions relative to siblings, but the usage 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.

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds a key behavioral guarantee: every capability is returned with both its evidence and limitation, and the tool cannot return one without the other. This goes beyond the annotations and provides useful context about the return structure.

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 concise sentences that front-load the primary action and the critical pairing invariant. Every word serves a purpose, with no filler or redundancy.

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 description explains the core lookup modes and the mandatory return pairing, which is the most important behavior. It does not explain the limit parameter or potential multiple results for topic searches, and there is no output schema to fill that gap. This leaves a minor ambiguity but the tool is still adequately described.

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 schema already documents id and topic, with 67% coverage. The description mostly restates the id formats (C-nn, L-nn) already present in the schema, and it does not clarify the limit parameter, which has no schema description. The description adds little beyond the schema for parameter understanding.

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 the specific verb 'Resolve' and identifies the resource as a capability from the claims ledger. It clearly outlines the three lookup modes (by id, by limitation id, or by topic), making its purpose unambiguous and distinct from sibling tools like check_job and search_docs.

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 provides clear context on when to use id versus topic lookup ('when the id is unknown'), which is a usage guideline. However, it does not explicitly mention alternatives or when not to use this tool relative to sibling tools, so it lacks explicit exclusions or comparisons.

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, and destructiveHint=false, so the description does not need to restate safety. It adds useful context by describing keyword matching rather than semantic search and by clarifying the returned shape (file path, heading, excerpt). No contradictions exists between the description and 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 two sentences, front-loaded with scope and return format, and does not waste words. The read-only note lightly overlaps with annotations but adds the important scope boundary that customer records are not returned. No padding or repetition.

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 simple, read-only search tool, the description covers the input (keyword query), the source corpus, and the output fields. The absence of an output schema is mitigated by the explicit return format in the description. It could add edge behavior such as empty results, but overall is sufficiently complete.

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 schema already describes query's matching behavior and limit's type, default, min, and max. The description adds context that the query searches documentation content, but does not mention the limit parameter or its behavior. The schema covers half of the parameters well, but the description adds only mild value for parameter meaning.

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 action ('Keyword search') and a precise resource ('this framework's documentation set') while enumerating the included document types. It clearly distinguishes itself from sibling tools like check_job and get_capability by targeting documentation lookup only.

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 provides clear context for when to use the tool: any time users need to search framework documentation. It also implies an exclusion by stating it never serves customer records, signaling this is not the tool for data access. However, it does not explicitly name alternative tools or give when-not-to-use scenarios beyond that.

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