LocalMark Agent Directory

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

No annotations are provided, so the description carries the burden. It usefully discloses behavioral facts beyond the schema: only *published* agents are retrievable, and it names the returned artifacts (source, declared skills, latest card check). However, it says nothing about auth requirements, error behavior when the ID is unknown, or permissions.

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 action and returned content front-loaded and zero filler. 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, the description correctly picks up the slack by enumerating what is returned. For a simple one-parameter read tool with no annotations this is close to complete, though the lack of any error or auth context leaves a small gap.

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 adds one meaningful fact — the identifier is a 'LocalMark ID' — but omits format, type expectation (the schema says integer), and how to obtain a valid ID. Partial compensation for a single undocumented parameter.

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 (Get) and resource (one published agent), and enumerates what is returned: source, declared skills, and latest card check. The singular 'one' implicitly separates it from list_agents and search_agents, though it never names them 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?

Usage is only implied: 'one published agent' suggests single-record lookup versus the sibling list/search tools, but there is no explicit when-to-use, when-not-to-use, or naming of alternatives. An agent can infer the intent but receives no routing guidance.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses deterministic ordering ('alphabetical order') and pagination stability, which are real behavioral traits, but says nothing about auth requirements, rate limits, or what a page of results looks like.

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 ordering and pagination behavior front-loaded and no filler. Nothing needs trimming.

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 two-parameter list tool with no output schema, the description covers the essentials of ordering and pagination but omits parameter meaning, default values, and result contents. It is minimally adequate but leaves gaps an agent would want filled.

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 explain limit and offset. 'Stable pagination' gestures at the offset/limit pattern but does not define either parameter, note the defaults (20/0), or explain how stability is maintained across pages.

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 (browse) and resource (published agents), plus ordering and pagination behavior. It implies a distinction from search_agents by describing an unfiltered alphabetical browse, but never names the sibling, so disambiguation is left to inference.

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 explicit when-to-use or when-not-to-use guidance. The phrase 'published agents' hints at a scope filter, but the description never contrasts this with search_agents (query-based) or get_agent (single record), so an agent must guess which sibling applies.

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?

With no annotations, the description carries the full burden. It usefully discloses the result shape (card and profile URLs, not task results) and that only public agents are searched, but says nothing about auth requirements, ranking, pagination, or result volume.

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 tight sentences with zero waste; the core purpose leads and the scope caveat follows immediately.

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 sentence about returning card/profile URLs rather than task results usefully substitutes for a return-value description. However, combined with no annotations and 0% parameter coverage, the definition leaves pagination and matching behavior unspecified.

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 detail at all. Both 'query' (matching semantics, exact vs fuzzy) and 'limit' (default 10, max value) are left entirely unexplained for the agent.

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 (public agents), plus the searched fields (names, descriptions, declared skills). It implicitly distinguishes itself from list_agents and get_agent by being a query-based search, though it never names 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?

Usage is implied: search when you have a query string rather than a known agent ID. The 'not task results' clause signals scope, but there is no explicit statement of when to prefer this over list_agents or get_agent.

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