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

Annotations already declare this as non-read-only and destructive, but the description adds valuable behavioral context: risky invocations require an approval token or env override, and idempotency_key plus retry/backoff are supported. It still leaves undefined what risky means and what side effects occur.

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 three short, front-loaded sentences with no filler. Purpose, gating requirements, and retry support are each communicated efficiently.

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 destructive six-parameter tool with nested objects, the description covers the key approval and retry mechanics, and an output schema exists. However, with very low schema description coverage, it should do more to explain reason, payload, and params semantics.

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 only 17%, so the description must compensate. It gives some meaning for capability, confirm, and idempotency_key, but it does not explain reason, payload, or the shape and semantics of params, leaving most parameters without meaningful guidance.

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 states a specific verb and resource: invoking an Echo SDK capability by exact capability ID with params. It is clear what the tool does, but it does not explicitly differentiate itself from the sibling tools search, write, and read.

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 an important usage condition for risky capabilities: confirm='SDK_INVOKE_APPROVED' unless ECHO_MCP_ALLOW_RISKY_SDK=1. However, it does not say when to use this tool versus alternatives such as search, write, or read, nor does it define what counts as a risky capability.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered by structured data. The description adds that an SDK capability read returns registration_state, which is useful content context, but it says nothing about max_bytes truncation behavior or what a directory read returns.

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 with no padding, though the dual-purpose phrasing ('or read one exact SDK capability record') is dense and slightly ambiguous about which parameters select which mode.

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?

An output schema exists, so return values need not be described. However, for a 5-parameter tool with 0% schema coverage and no usage guidance, the description leaves the parameter disambiguation and truncation behavior unexplained, which is not enough for an agent to call it reliably.

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 5 parameters, so the description carries the burden and largely fails. It hints that 'path' serves file/directory reads and that 'id'/'capability'/'target=sdk_cap' serve capability reads, but it never explains the id-vs-capability distinction, the target enum default, or what max_bytes (default 262144) truncates.

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 (read) and two distinct resources: a local file/directory and a single SDK capability record. This differentiates it from the sibling invoke_sdk_cap (an action, not a read) and implicitly from search, though it never explicitly contrasts with search or write.

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 guidance or exclusion. The phrase 'one exact SDK capability record' hints at exact-match lookup versus search, but the agent is left to infer that routing decision on its own.

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. The description adds the scope of what is searched (local FS plus registry) and the registration-probe behavior, but says nothing about result ordering, limits interaction, or cost of a 'both' search.

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 compact sentences, front-loaded with the core action and immediately followed by the mode enumeration and the special-case recipe. The only waste is the redundant self-referential tool identifier in parentheses.

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 9 parameters, only 33% schema coverage, and two distinct search domains, the description covers the primary usage path adequately and an output schema exists so return values need not be explained. It still leaves the file-search parameters (root, pattern, include_content) and the interaction between targets and max_results unexplained for a tool of this complexity.

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 only 33%, so the description must compensate, and it does explain target, health, query, and check_ids semantics beyond the raw enum values. However root, pattern, include_content, max_results, and cap_ids receive no treatment in the description, leaving roughly half the surface 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 (Search) and two concrete resources: local files/directories and the Echo SDK capability registry, with the target modes enumerated. It is clearly distinguishable from siblings like read, write, and invoke_sdk_cap, though the parenthetical repeating the tool's own name (mcp__claude_ai_EchoOmegaPrime__search) is confusing noise rather than clarification.

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 an explicit routing rule: use target=sdk_caps with query='red unregistered' for red/unregistered grounding, and check_ids for exact registration probes. That is real when-to-use guidance for one scenario, but it never states when to prefer files vs both, nor when to reach for read or invoke_sdk_cap instead.

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 destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavior: idempotency via idempotency_key, content-hash idempotency for overwrite, and the absence of any delete path, clarifying what the destructive hint does and does not mean.

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 short sentences with zero filler; the core action is front-loaded and the idempotency/scope caveats follow. Every clause carries 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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description rounds this out with idempotency and delete-scope notes, though it could say more about whether overwrite destroys prior content or what permissions are required.

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 only 20% (only idempotency_key is documented), so the description must compensate. It does add real meaning for mode (overwrite vs append) and idempotency_key, but leaves path, content, and create_dirs to be inferred from their names alone.

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 pair ("Write or append UTF-8 text to a local file path") with scope qualifiers (UTF-8, local path). The mutating verb inherently separates it from the `read` sibling, and the append/overwrite modes are named.

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 one useful boundary ("No delete operation is exposed") and hints at retry semantics, but never says when to choose append vs overwrite or when to prefer this over the `read`/`search` siblings. Usage is implied rather than stated.

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