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

No annotations exist, so the description carries the full behavioral burden. It mentions the corpus (local network, several sources) but says nothing about permissions, whether retrieval is read-only, latency, or result set behavior. With 7 parameters and no annotations, this 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?

Two short sentences, purpose front-loaded in the first, context in the second, with no filler. It is efficient, though it borders on under-specified for a 7-parameter retrieval 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 7-parameter cross-modal retrieval tool with no annotations and no output schema, the description omits the query/target relationship, result behavior, and any operational constraints. The rich schema compensates for parameter meaning, but the description leaves key behavioral questions unanswered.

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 100%, so every parameter is already documented, including the subtle query/target interaction and the filter syntax. The description's 'visually similar and metadata-related' phrasing loosely echoes those semantics but adds no format or syntax detail beyond the schema, so baseline 3 applies.

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 ('Find ... images') and qualifies the retrieval modality ('visually similar and metadata-related'), which is more informative than a bare 'search'. It does not name or contrast with its sibling tag_image, 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?

The second sentence gives a usage context ('cross-modal retrieval over images from several sources across the local network'), which implies when the tool is appropriate. However, it names no alternatives and gives no when-not conditions, so usage is only implied rather than specified.

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 and mostly doesn't. It discloses persistence ('persistent tags') and a server dependency, but says nothing about side effects, whether remove_all_tags is destructive, permissions, or reversibility. The action-level semantics live in the schema, not the description.

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?

One sentence of purpose followed by two compact, front-loaded examples. Nothing is wasted, though the examples lean toward illustration over instruction and could have carried routing guidance instead.

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?

No output schema exists, so the description should ideally indicate what list_tags/show_tag return, and it does not. Combined with missing when-to-use guidance and no annotations, this is adequate but leaves gaps an agent would have to resolve by trial.

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 100%, so the schema already documents tags, action, target, and scratchpadFolder in detail. The examples reinforce the anyOf string/array shape for target and tags, which is mildly additive, but the baseline for full schema coverage is 3.

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: managing persistent tags for indexed images via the configured image server. It is clearly distinct from the sibling find_image, though it never explicitly says so. A reasonable agent can tell what it does without opening the 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?

The two examples show invocation patterns for add_tag and remove_tag, which implies usage, but there is no statement of when to choose a given action or when to prefer this tool over alternatives. The list_tags/show_tag/remove_all_tags actions are never demonstrated or contextualized.

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