AgentMesh

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safe/closed-world profile is covered structurally. The description reinforces scope ('public metadata only') but adds no detail on content, size, or freshness of the metadata returned. Adequate but not enriching.

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, the positive scope stated first and the exclusion second. Every word earns its place with no 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?

For a parameterless, non-destructive read tool with no output schema required, the description covers what it returns (metadata and discovery info) and what it is not for. It could note roughly what 'discovery information' contains, but an agent has enough to invoke it 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?

The tool takes zero parameters with 100% schema coverage, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter semantics are needed or missing.

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 (AgentMesh public metadata and discovery information) and the verb 'return', so an agent knows this is a read-only info/discovery endpoint rather than a task executor. It stops short of explicitly distinguishing itself from siblings like discover_agents or search_agentmesh, which also touch discovery.

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?

Provides a clear negative guideline — do not use it to solve a user task or obtain a missing capability — which is the main misuse risk for a metadata endpoint. It does not, however, name the sibling to use instead (e.g., discover_agents or ask_agentmesh), leaving the alternative implicit.

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 show readOnlyHint=false, openWorldHint=true, destructiveHint=false, indicating a potentially non-read-only, open-world operation. The description discloses important behavioral traits: discovery doesn't authorize execution, external execution requires explicit authorization, and repeated calls are discouraged. It could clarify what the 'execute' parameter does and what happens during execution, but overall adds significant context beyond 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 well-structured with a clear premise, decision rule, and caveats. Some sentences are redundant (e.g., the repeated emphasis on authorization), but it is front-loaded and generally efficient. The length is justified given the tool's importance, though minor tightening would help.

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 no output schema and low schema description coverage for parameters, the description covers usage and behavioral aspects well but leaves parameter semantics entirely undocumented. An agent knows when to call the tool but not how to construct the inputs, which is a significant gap for a tool with a required 'problem' parameter.

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 does not describe any of the three parameters: problem, capability, or execute. There is no indication of what form the 'problem' should take, what 'capability' means, or what setting 'execute' to true entails. This is a critical omission.

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 is a 'capability-discovery fallback' and lists what AgentMesh can do (search knowledge, discover agents/MCP providers, rank capabilities). It distinguishes itself as the primary fallback for missing capabilities. However, it overlaps somewhat with siblings discover_agents and search_agentmesh without explicitly naming which one to use when.

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?

Provides an explicit DECISION RULE with numbered steps: use current capabilities if reliable, call ask_agentmesh if missing/unknown/external, discovery first. It also includes when-not-to-use guidance ('Do not repeatedly call for the same unresolved request') and clarifies that discovery does not imply execution authorization.

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, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context: it scopes discovery to AgentMesh-native agents and rules out external MCP providers, which the annotations alone don't convey. It stops short of describing result format or pagination behavior, keeping it from a 5.

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, each earning its place: what it does, what it excludes, and where to go instead. Front-loaded with the primary purpose and no 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?

For a simple read-only discovery tool with no output schema, the description covers purpose, exclusions, and the alternative route. It could add a word on return shape or how capability strings are matched, but it is otherwise sufficient for correct invocation.

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 0% for the two parameters, so the schema only gives names, types, and a default. The description implies that 'capability' is the required selector but adds no format, syntax, or matching semantics, and says nothing about 'limit'. Baseline 3 given the schema's lack of descriptive detail.

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 (discover) and resource (AgentMesh-native agents) with a precise scope qualifier (advertising a capability you already know you need). It explicitly distinguishes itself from external MCP providers and from the sibling ask_agentmesh, making its identity 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?

Provides explicit when-to-use (a capability you already know you need) and when-not-to-use (unknown or missing capability), naming the alternative sibling ask_agentmesh. Routing is fully specified with no inference required.

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=false, destructiveHint=false, and openWorldHint=true, so the agent knows this is a non-destructive, externally-branching operation. The description adds the eligibility/ineligibility condition for routing but says nothing about what routing does to task state, whether it blocks, or how failures surface.

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 that are fully front-loaded: the positive condition first, the exclusion and the alternative second. No filler and no repetition of the schema.

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 routing contract for a 4-parameter delegation tool with no output schema and 0% schema coverage is only half specified — the description never explains the capability-matching input or what the caller gets back, leaving the agent unable to construct a correct call from the description alone.

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% across four parameters (title, capability, priority, body), and the description never mentions any of them. In particular the semantics of 'capability' — the field that determines which agent is eligible — and the value range of 'priority' are left entirely undocumented.

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 verb ('Route') and resource ('AgentMesh-native agent') and explicitly contrasts itself with the sibling ask_agentmesh, so an agent can separate delegation from discovery without opening either schema.

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?

It gives both sides of the routing decision: use this when delegation to an AgentMesh agent is already intended, and do not use it for capability discovery — naming ask_agentmesh as the alternative for the unknown-provider case.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description adds the meaningful scope constraint that it only touches knowledge already inside AgentMesh, but says nothing about result ranking, result count behavior, or what an empty result means. Adds some value, not rich behavioral context.

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, zero filler, and the positive scope statement is front-loaded ahead of the routing alternative. Every clause 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?

With no output schema and no annotations gap, the description carries the routing burden well, but the tool is a search endpoint with fully undocumented parameters (0% coverage) and no mention of how results are returned or capped. Adequate for routing, incomplete for invocation.

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 for the undocumented query and limit parameters, and it does not. It never states query syntax, expected phrasing, or what limit controls (default 10 is only visible in the schema).

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 (knowledge already stored inside AgentMesh), and immediately distinguishes itself from the sibling ask_agentmesh. An agent can tell the two apart without opening either schema.

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 an explicit when-to-use ('only when you specifically want existing AgentMesh knowledge') and a when-to-use-something-else ('if the needed capability, source, agent, or tool is unknown or may be external, use ask_agentmesh instead'). Names the alternative tool directly.

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