mkt_capabilities

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

With no annotations supplied, the description carries the full burden, and it does deliver the single most important behavioral fact: this is read-only and therefore safe to call without side effects. Beyond that it says nothing about return format, result size, whether lookups are paginated, or what happens when role_family/capability_id are omitted, which for a zero-annotation tool is a meaningful gap.

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 front-loaded sentence that establishes read-only status and scope immediately, with zero filler. It is efficient, but the brevity is partly achieved by omitting parameter and usage information rather than by careful editing.

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?

Three parameters at 0% schema coverage, no annotations, and no output schema means the description is the only documentation an agent has — and it explains none of the parameters. For a tool with optional filters whose default behavior (no filters) is undefined, this leaves too much to guesswork.

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 no parameter meaning. 'role_family' is faintly inferable from '岗位族', but 'capability_id' and especially 'lint' (a boolean that is not a natural filter for a registry lookup) are entirely unexplained — an agent cannot tell whether lint enables validation output or filters lint-flagged entries.

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 the resource precisely — a read-only GTM capability registry — and quantifies its scope (18 capability domains, 40 role families) along with the content types it holds (responsibilities, KPIs, SOPs, deliverables, approval mappings). It is clearly a reference/lookup tool, which separates it from action-oriented siblings like mkt_optimize or mkt_workflow, though it never explicitly names which sibling it is the alternative to.

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. The word '只读' implies this is a consult-only lookup, but the description never says when an agent should consult the capability registry versus mkt_playbooks, mkt_experience, or mkt_search, nor does it describe prerequisites or typical follow-up actions after retrieving a capability.

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