Create a tamper-evident Evidence Pack for a public URL (screenshot + PDF + HTML + signed/timestamped manifest). NOT an affidavit or court filing. Output: { id, status, poll, verify path }. Costs 10 credits.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTPS URL to capture | |
| full_page | No | ||
| pack_type | No | standard | |
| retention_days | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations declare readOnlyHint=true, but the description says 'Create' and 'Costs 10 credits,' which describes a state-changing, side-effectful operation. This directly contradicts the read-only annotation. The description also fails to explain implications of the openWorldHint annotation. This is an Annotation Contradiction.
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 compact and well-structured: it front-loads the core action, parenthetically lists the pack components, then adds the non-goal, output shape, and cost. Every sentence adds useful information without redundant restatement of the tool name or title.
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 there are four parameters, no output schema, and an annotation contradiction, the description is not complete enough. It does state the output shape and cost, but it omits the meaning of full_page, pack_type, retention_days, poll, and verify path, and it fails to reconcile the readOnlyHint contradiction. An agent will likely mis-estimate side effects or parameter choices.
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 only 25%; only 'url' has a schema description. The tool description does not compensate for the other three parameters: full_page, pack_type, and retention_days are entirely undocumented in both the schema and the description, including their defaults and enums. An agent cannot correctly choose or set these parameters based on available text.
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 and resource: 'Create a tamper-evident Evidence Pack for a public URL' and enumerates the contents (screenshot + PDF + HTML + signed/timestamped manifest). It also clarifies what it is not ('NOT an affidavit or court filing') and gives the output shape, making the tool's purpose distinct and actionable.
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 description implies when to use the tool — when an evidence pack is needed for a public URL — but gives no explicit guidance about when to prefer alternatives like forgekit_capture_screenshot, forgekit_render_pdf, forgekit_ship_pack, or forgekit_ship_bundle. The only exclusion, 'NOT an affidavit or court filing,' is a legal-context disclaimer rather than a tool-selection guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
ship_verify and ship_verify_v2 are near-synonyms, and ship_bundle wraps ship_pack plus an audit while evidence_pack combines screenshot/PDF/HTML. The descriptions help, but an agent could easily pick the wrong granularity or version.
All tools use the forgekit_ prefix and snake_case, but verb placement is inconsistent: business_days_add/count place the noun first, evidence_pack has no verb, and the ship_* group mixes noun and verb senses. The set is readable but not uniformly patterned.
Fifteen tools is near the upper end of a reasonable utility-kit size, and most tools are individually useful. It feels slightly over-scoped because ship_verify_v2 and ship_bundle partially duplicate other capabilities rather than adding clearly new operations.
The web/media surface is broadly covered with screenshots, PDFs, QR encode/decode, OG previews, evidence packs, and agent-readiness audits. However, the set is an eclectic collection rather than one coherent workflow, and there are gaps such as no MCP-level polling for async jobs and no history/retrieval for evidence packs or ship bundles.